© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25433
    Prev
    Next
    INDEX
    Explanations

    Noisy text

    np_max-act · gemini-2.0-flash

    tokens containing digits or leetspeak-style characters/symbols (e.g., sequences of numbers and substitution symbols).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赂
    -0.08
    重伤
    -0.07
    ObjectId
    -0.07
    帏
    -0.07
    BST
    -0.07
     תה
    -0.07
    otec
    -0.07
    ToAdd
    -0.07
    报名
    -0.07
    itemap
    -0.07
    POSITIVE LOGITS
    0.07
    呼ばれ
    0.07
     않는다
    0.07
     Когда
    0.07
                              ↵
    0.07
    0.07
    🛩
    0.06
    根据
    0.06
    IDDEN
    0.06
     zipper
    0.06
    Activations Density 0.054%

    No Known Activations