© 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. 24655
    Prev
    Next
    INDEX
    Explanations

    Indian history and mythology

    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
    魃
    -0.09
    建党
    -0.08
    ед
    -0.07
    glyphicon
    -0.07
    גשת
    -0.07
    귁
    -0.07
    ប
    -0.07
    [parent
    -0.07
    喜
    -0.07
    pkg
    -0.07
    POSITIVE LOGITS
     sorts
    0.07
     consequential
    0.07
     cracks
    0.07
     Adjustable
    0.07
    .points
    0.07
    .getFloat
    0.07
     dangling
    0.07
     Utf
    0.07
    ........................
    0.07
    也就是说
    0.07
    Activations Density 0.001%

    No Known Activations