© 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. 131217
    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
    çļĦçݰ象
    -0.28
    ä¸Ŀ绸ä¹ĭè·¯
    -0.27
    Though
    -0.26
    룬
    -0.25
    ç»ıå¼Ģ
    -0.24
    çħ§æł·
    -0.24
    cken
    -0.24
    çŃ·åŃIJ
    -0.24
    getRequest
    -0.23
    åĽłåľ°
    -0.23
    POSITIVE LOGITS
    opal
    0.30
    æĦı大
    0.27
     res
    0.26
     terminated
    0.25
    _sets
    0.24
     satisfied
    0.24
     Units
    0.23
    ża
    0.23
    åĨ¬
    0.23
    éªĿ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.