© 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. 17738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æł¹æį®ä¸įåIJĮ
    -0.31
    çļĦåıijå±ķ
    -0.26
    ServletResponse
    -0.26
    icamente
    -0.26
    essen
    -0.26
    ystone
    -0.26
    inode
    -0.25
    Loc
    -0.25
    hoot
    -0.25
    ÅĽci
    -0.25
    POSITIVE LOGITS
    ä¸īæĿ¡
    0.32
    第ä¸ĢæĿ¡
    0.29
    -aligned
    0.27
    两æĿ¡
    0.26
    tracts
    0.25
    registers
    0.25
    æ´µ
    0.24
    æĿ¡
    0.24
    _CAST
    0.24
    Strings
    0.24
    Activations Density 10.799%

    No Known Activations

    This feature has no known activations.