© 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. 27-TRANSCODER-HP
    7. 8082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axe
    -0.29
    usan
    -0.27
    ucha
    -0.25
    ä»İæĿ¥ä¸į
    -0.25
    keit
    -0.23
    ademic
    -0.23
    ä¿¡
    -0.23
    uche
    -0.23
    apel
    -0.23
     rails
    -0.23
    POSITIVE LOGITS
     declined
    0.33
     Shank
    0.27
    åħ¨éĿ¢èIJ½å®ŀ
    0.25
     declines
    0.25
    åīĬåĩı
    0.25
     Conserv
    0.24
    åįłåľ°éĿ¢ç§¯
    0.24
     wo
    0.24
     behind
    0.24
    Li
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.