© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nez
    -0.26
    åķĨ
    -0.26
    çĢĽ
    -0.25
    ered
    -0.25
    IONS
    -0.25
     thrift
    -0.23
    æŀķ头
    -0.23
    pile
    -0.23
    解åĨ³æĸ¹æ¡Ī
    -0.23
    åĸĦ
    -0.23
    POSITIVE LOGITS
    èIJ½åľ¨
    0.25
     coordin
    0.24
    è·Łä¸įä¸Ĭ
    0.24
    _DR
    0.23
    .CreateCommand
    0.23
    为大家
    0.22
     bay
    0.22
     coordinate
    0.22
     dernier
    0.22
     coordinated
    0.22
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.