© 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. 20-TRANSCODER-HP
    7. 142201
    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
    Not in Any Lists

    No Comments

    Negative Logits
    elijke
    -0.26
    ARIANT
    -0.26
    rlen
    -0.25
    roup
    -0.25
    iones
    -0.25
    ç²¾ç¥ŀ
    -0.24
    @↵
    -0.24
    onnen
    -0.24
    å¼Ģåı£
    -0.24
    endet
    -0.23
    POSITIVE LOGITS
    zer
    0.31
     incompatible
    0.26
    æĭ¥æĬ±
    0.26
    è´¸æĺĵ
    0.26
    åIJĮç±»
    0.24
    æīĵæŃ»
    0.24
     Lor
    0.24
     deny
    0.24
     Err
    0.24
     Bend
    0.24
    Activations Density 6.375%

    No Known Activations

    This feature has no known activations.