© 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. 97049
    Prev
    Next
    INDEX
    Explanations

    blood coagulation

    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
    lx
    -0.25
    iders
    -0.25
    çļĦ主é¢ĺ
    -0.24
    owy
    -0.24
    addy
    -0.24
     treÅĽci
    -0.24
    ikal
    -0.23
    ikt
    -0.23
    hra
    -0.23
    .bt
    -0.23
    POSITIVE LOGITS
    _TYPEDEF
    0.28
    ä¸įä½ı
    0.25
    æµģ
    0.25
    æľºä¼ļ
    0.25
    åİ»
    0.24
    åIJij
    0.24
    olum
    0.24
    oland
    0.24
    éĩįè¦ģä½ľçĶ¨
    0.24
     insult
    0.23
    Activations Density 0.052%

    No Known Activations