© 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. 15-RESID-POST-AA
    11. 123152
    Prev
    Next
    INDEX
    Explanations

    rebate

    np_max-act · gemini-2.0-flash
    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
    Decl
    -0.07
    NumberOf
    -0.07
     rencontre
    -0.07
    Severity
    -0.07
    飲
    -0.07
    👗
    -0.07
    _menu
    -0.07
    _find
    -0.07
    🄶
    -0.07
    ':↵↵
    -0.07
    POSITIVE LOGITS
    结局
    0.09
    初中
    0.08
     BaseModel
    0.07
    痴
    0.07
    人死亡
    0.07
    嬰
    0.07
    ,buf
    0.07
    律师事务
    0.07
    电视剧
    0.07
    ものが
    0.07
    Activations Density 0.005%

    No Known Activations