© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 114972
    Prev
    Next
    INDEX
    Explanations

    Advice/Opinions

    np_max-act · gemini-2.0-flash

    requests that aim to manipulate or coerce romantic interest, triggering refusal-style, ethics/consent-focused responses.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    requests to coerce or manipulate someone into romantic feelings and the corresponding ethical, consent-focused refusal responses.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    предел
    -0.07
    kg
    -0.07
    Lemma
    -0.07
    协议
    -0.07
    noun
    -0.07
     GSL
    -0.07
     libs
    -0.06
    拆除
    -0.06
    之家
    -0.06
     ATK
    -0.06
    POSITIVE LOGITS
    뙇
    0.07
    مقار
    0.07
    づくり
    0.07
    岙
    0.07
    entities
    0.07
    🌪
    0.07
    渍
    0.07
    Choice
    0.06
    .Pattern
    0.06
    묫
    0.06
    Activations Density 0.084%

    No Known Activations