© 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. 88811
    Prev
    Next
    INDEX
    Explanations

    Code and technical descriptions

    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
     ext
    -0.26
    èĩªçĶ±è´¸æĺĵ
    -0.25
    azzi
    -0.25
     gam
    -0.24
    æ¯į
    -0.24
    ics
    -0.24
    iren
    -0.23
     usage
    -0.23
    ICS
    -0.23
    un
    -0.23
    POSITIVE LOGITS
    èĤ¥
    0.25
    sonian
    0.25
    ancode
    0.24
     {_
    0.24
    æ±Ń
    0.24
    /dist
    0.23
     stringWith
    0.23
    ozilla
    0.23
    éĥ¨å§Ķ
    0.23
    .bel
    0.22
    Activations Density 0.004%

    No Known Activations