© 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. 130575
    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
    è¯Ŀ
    -0.29
     Su
    -0.26
    atto
    -0.25
     conven
    -0.25
     afs
    -0.24
    ael
    -0.23
     czÄĻÅĽÄĩ
    -0.23
    ×ķ×Ļ
    -0.23
    ä¸Ģç«Ļ
    -0.23
     su
    -0.22
    POSITIVE LOGITS
     pinch
    0.24
    åĿĩä»·
    0.23
     facility
    0.23
     impunity
    0.23
    tors
    0.23
    éķ¿ä¸īè§Ĵ
    0.23
    icos
    0.22
    ãģĿãģĵãģ§
    0.22
    åĢ¾æĸľ
    0.22
    åѦä¸ļ
    0.22
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.