© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    messed up

    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_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
    真正做到
    -0.07
    ICC
    -0.07
     lesion
    -0.06
    \Model
    -0.06
    函
    -0.06
     ])↵
    -0.06
    ألعاب
    -0.06
     Mechanical
    -0.06
    /#{
    -0.06
    Statement
    -0.06
    POSITIVE LOGITS
    岸边
    0.07
    ideshow
    0.07
    >J
    0.07
     Ris
    0.07
     Daisy
    0.07
    .So
    0.06
    رة
    0.06
    诗意
    0.06
    /month
    0.06
    预防
    0.06
    Activations Density 0.137%

    No Known Activations