© 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. 88985
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    alars
    -0.29
    uzzi
    -0.28
    ombs
    -0.26
    áb
    -0.26
    é¡¿
    -0.26
     deduct
    -0.25
    ework
    -0.25
     Bonus
    -0.25
    htdocs
    -0.25
     Replies
    -0.25
    POSITIVE LOGITS
    g
    0.28
     explo
    0.27
    Sort
    0.27
    .&
    0.27
    .X
    0.27
    çļĦæĸĩç«ł
    0.26
    lo
    0.26
    åŃIJ
    0.26
    ive
    0.26
    time
    0.26
    Activations Density 0.008%

    No Known Activations