© 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. 7701
    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
    æĮģèĤ¡
    -0.27
    æ°´åĪ©
    -0.25
    Ñĥг
    -0.24
    ispens
    -0.24
    éĴľ
    -0.23
     g
    -0.23
    樾
    -0.23
    æĺ¯ä½ł
    -0.23
    .Face
    -0.23
    éĥ½æĹłæ³ķ
    -0.23
    POSITIVE LOGITS
    _ENDIAN
    0.31
    edo
    0.26
     eyel
    0.26
    dde
    0.26
    ropp
    0.26
    ẳ
    0.25
    noon
    0.25
     <![
    0.25
    好æĦŁ
    0.24
    athed
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.