© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 113125
    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
    Negative Logits
    æŀķ
    -0.27
    ALAR
    -0.24
     unwind
    -0.23
    èĭ¦ç¬ij
    -0.23
    ActionBar
    -0.23
    perse
    -0.23
    .Support
    -0.23
    ç©ij
    -0.23
    èĭįçĻ½
    -0.23
    åĩºåľŁ
    -0.23
    POSITIVE LOGITS
     scope
    0.28
     Scope
    0.24
     scopes
    0.24
    amm
    0.24
     consequ
    0.23
    æİ¢
    0.23
    ä¸ĵå±ŀ
    0.23
    uffy
    0.23
    ç®Ģ
    0.23
    à¸ĸา
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.