© 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. 58623
    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
    urga
    -0.30
    ading
    -0.28
    rapped
    -0.25
     errno
    -0.25
    ë¡ł
    -0.24
    罨
    -0.23
    pedia
    -0.23
    -ready
    -0.23
    èĥĸ
    -0.23
    tracts
    -0.23
    POSITIVE LOGITS
    義åĭĻ
    0.30
    ç¼İ
    0.25
     Pattern
    0.25
     Mits
    0.25
     expects
    0.25
    çĸ¾
    0.25
    ä½ıåĿĢ
    0.25
    æŃ¥
    0.25
    åľ¨åľ°ä¸Ĭ
    0.24
     Glück
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.