© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19988
    Prev
    Next
    INDEX
    Explanations

    rights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hea
    -0.27
     troubles
    -0.27
     gen
    -0.25
    æĬķåħ¥
    -0.24
    oru
    -0.24
    RAIN
    -0.23
    çļĦ缮æłĩ
    -0.23
    å¹¶åľ¨
    -0.23
     march
    -0.23
     trouble
    -0.23
    POSITIVE LOGITS
     Scotia
    0.28
    çķĮ
    0.28
    brids
    0.27
    izedName
    0.27
    partials
    0.26
    æ¢Ń
    0.25
    .af
    0.25
    allah
    0.24
    大æĪ·
    0.24
    ota
    0.24
    Activations Density 0.007%

    No Known Activations