© 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. 20-TRANSCODER-HP
    7. 106788
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     rings
    -0.26
    ä¿ĺ
    -0.26
    ijľ
    -0.25
    bury
    -0.25
    tics
    -0.25
     cita
    -0.25
    warts
    -0.24
     refer
    -0.24
    atory
    -0.24
    æĿĢ
    -0.23
    POSITIVE LOGITS
    主æĴŃ
    0.27
    Translator
    0.25
     Scientists
    0.24
    _SUITE
    0.24
    åĨµ
    0.23
    éĻ¢åŃIJéĩĮ
    0.23
    fsp
    0.23
    ä½ľèĢħæīĢæľī
    0.23
    virtual
    0.23
    artist
    0.23
    Activations Density 19.361%

    No Known Activations

    This feature has no known activations.