© 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. 112246
    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
     afr
    -0.26
    áĥ§
    -0.25
    èĥ½æĬĬ
    -0.24
     AL
    -0.23
     Rational
    -0.23
    fall
    -0.23
    Stopped
    -0.23
    Rated
    -0.23
    аÑĢам
    -0.23
     ratings
    -0.23
    POSITIVE LOGITS
    干线
    0.30
    äºĮ楼
    0.28
    è±¢
    0.25
    ÑĤÑĥÑĢ
    0.24
    utzer
    0.23
    idian
    0.23
    _FD
    0.23
     Compiled
    0.23
    VILLE
    0.23
    assage
    0.23
    Activations Density 0.116%

    No Known Activations

    This feature has no known activations.