© 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. 99045
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    åĬłå¿«æİ¨è¿Ľ
    -0.26
    æĪĴæĮĩ
    -0.25
    åŀ¤
    -0.24
    æ¼ł
    -0.24
    preferred
    -0.24
    æİ¥åĬĽ
    -0.24
    unning
    -0.23
     viewer
    -0.23
    çīĪæĿĥ声æĺİ
    -0.23
    pNext
    -0.23
    POSITIVE LOGITS
    æľºåħ³
    0.28
    ress
    0.26
    ché
    0.26
    èݺ
    0.25
     prób
    0.25
    éĦ±
    0.23
    声
    0.23
    _SD
    0.23
    orph
    0.23
    +S
    0.23
    Activations Density 0.075%

    No Known Activations