© 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. 18-TRANSCODER-HP
    7. 88126
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç³Ĭ
    -0.28
    å§Ķ
    -0.26
    FO
    -0.26
    ç´ł
    -0.26
     hy
    -0.25
    fte
    -0.24
    agrams
    -0.24
     interchange
    -0.24
    aring
    -0.23
    ä¸īåĽĽ
    -0.23
    POSITIVE LOGITS
    å¿ĥè¡Ģ
    0.26
    éĩijåŃĹ
    0.26
    Aj
    0.26
    lesia
    0.25
    ker
    0.25
    Negative
    0.24
    åIJijå¾Ģ
    0.24
    ç»ıæµİæįŁå¤±
    0.24
    Peak
    0.24
    轩
    0.24
    Activations Density 2.386%

    No Known Activations

    This feature has no known activations.