© 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. 98476
    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
     final
    -0.25
    cies
    -0.24
    ç»Ī究
    -0.24
    _FINAL
    -0.24
    ford
    -0.24
    ered
    -0.24
    Final
    -0.23
    æĢ»ç®Ĺ
    -0.23
    -btn
    -0.23
    FINAL
    -0.23
    POSITIVE LOGITS
    @student
    0.34
     trilogy
    0.24
    é¢Ĭ
    0.24
    ulner
    0.24
     Preconditions
    0.23
     Bieber
    0.23
    çݩ家æĿ¥è¯´
    0.23
    ogi
    0.23
     Juda
    0.23
     czÄĻÅĽÄĩ
    0.23
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.