© 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. 48843
    Prev
    Next
    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    boilerplate self-identification as an AI assistant along with stock disclaimers about lacking feelings, preferences, or a physical body.

    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
    是在
    -0.08
    _mapping
    -0.08
    EHICLE
    -0.07
    úsqueda
    -0.07
    FORMAT
    -0.07
    ucle
    -0.07
     emerging
    -0.07
    Rose
    -0.07
    .Step
    -0.07
     retrieved
    -0.07
    POSITIVE LOGITS
     prova
    0.07
    ᖕ
    0.07
     рук
    0.06
    ᄄ
    0.06
     От
    0.06
    MARK
    0.06
    أسباب
    0.06
    震动
    0.06
     требова
    0.06
    に行って
    0.06
    Activations Density 0.169%

    No Known Activations