© 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. 27-TRANSCODER-HP
    7. 56331
    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
    Negative Logits
    ç¥ŀç»ı
    -0.31
    minate
    -0.26
     Tensor
    -0.24
    <TResult
    -0.24
    mania
    -0.24
     TString
    -0.24
    ding
    -0.23
    妻åŃIJ
    -0.23
    ookies
    -0.23
     neural
    -0.23
    POSITIVE LOGITS
    Suit
    0.28
    vig
    0.25
    Affected
    0.24
    éĶĿ
    0.24
    åij¼åĴĮ
    0.24
     Canton
    0.24
    èµ°å¾Ĺ
    0.24
     bip
    0.23
     Banc
    0.23
    å¹³åĿĩæ°´å¹³
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.