© 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. 112765
    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
     war
    -0.27
    (ok
    -0.27
     Destination
    -0.25
    èIJ¥åĪ©
    -0.25
     subscri
    -0.24
    幸
    -0.24
    .focus
    -0.24
    _destination
    -0.23
    undo
    -0.23
     luck
    -0.23
    POSITIVE LOGITS
    åı¥
    0.29
    éļı
    0.27
    dling
    0.25
     Heard
    0.25
    ithe
    0.24
     slipped
    0.24
    çIJĨ论
    0.24
    ç»ĻåĩºäºĨ
    0.24
     flo
    0.24
    ä¸įä¸ĭ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.