© 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. 32-TRANSCODER-HP
    7. 40932
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    åĴĮå¹³
    -0.28
    åį±éĻ©
    -0.28
    ransition
    -0.27
    æľ¬ä¹¦
    -0.26
    odate
    -0.26
    èĭ¦éļ¾
    -0.25
     peace
    -0.24
    åİŁåĽł
    -0.24
    é¦Ļæ°´
    -0.24
    ArrayOf
    -0.23
    POSITIVE LOGITS
    tracted
    0.28
    Residents
    0.25
    ushman
    0.25
     MPU
    0.24
    udging
    0.24
    ighting
    0.24
     blinds
    0.24
    оÑĤоÑĢ
    0.24
     oct
    0.23
    ç§ĭåŃ£
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.