© 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. 30678
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    Take
    -0.07
     gev
    -0.07
     miệ
    -0.07
     perfor
    -0.07
    inkel
    -0.06
    Wild
    -0.06
    Scalars
    -0.06
    ح
    -0.06
    Flat
    -0.06
    蒴
    -0.06
    POSITIVE LOGITS
    ‗
    0.08
    $name
    0.07
    $content
    0.07
    /comment
    0.07
    릎
    0.07
     Elections
    0.07
     Tess
    0.07
    /email
    0.07
    蚓
    0.07
    Age
    0.07
    Activations Density 0.020%

    No Known Activations