© 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. 111133
    Prev
    Next
    INDEX
    Explanations

    heritage

    np_max-act · gemini-2.0-flash
    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
    YC
    -0.28
    umo
    -0.24
    ç§ijæĬĢåĽŃ
    -0.24
    çļĦçĬ¶æĢģ
    -0.24
    outh
    -0.23
    ually
    -0.23
    请éĢīæĭ©
    -0.23
    orus
    -0.23
    纲
    -0.23
    饷
    -0.23
    POSITIVE LOGITS
    ä¼łæĴŃ
    0.25
     close
    0.25
    _AC
    0.25
     classic
    0.24
    ç»ıåħ¸
    0.24
     exponent
    0.24
    ew
    0.24
     classical
    0.23
     due
    0.23
    æ²IJæµ´
    0.23
    Activations Density 0.112%

    No Known Activations