© 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. 17975
    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
     SG
    -0.28
    éĥ½ä¸įæĺ¯
    -0.27
    imetype
    -0.27
    ãĥªãĥ³ãĤ°
    -0.26
    idget
    -0.25
    ãĥ©ãĤ¤ãĥĪ
    -0.24
    ogue
    -0.24
    íĮħ
    -0.24
    ä¸ĭæĿ¥
    -0.24
    еÑĢиал
    -0.24
    POSITIVE LOGITS
    çģ°
    0.26
    eda
    0.24
    ELS
    0.24
    åįĬå²Ľ
    0.24
     ensl
    0.24
    åħļç»Ħ
    0.24
    rese
    0.24
     Har
    0.24
     Че
    0.23
    arsi
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.