© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43287
    Prev
    Next
    INDEX
    Explanations

    Att

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptom
    -0.31
    utos
    -0.29
     Att
    -0.28
    urses
    -0.28
    _Input
    -0.27
    esModule
    -0.26
    _ATT
    -0.26
    batim
    -0.26
    åŀĵ
    -0.26
    ãĤŃãĥ¥
    -0.26
    POSITIVE LOGITS
    ame
    0.31
    é£İ
    0.30
    ane
    0.29
    éĽĢ
    0.29
    ARN
    0.29
    æĪ¢
    0.28
    amel
    0.28
    風
    0.27
    AME
    0.27
    illin
    0.26
    Activations Density 0.005%

    No Known Activations