© 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. 33-TRANSCODER-HP
    7. 54712
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    doc
    -0.27
    ungi
    -0.26
    ä½ĵ
    -0.26
    cape
    -0.26
    icks
    -0.25
    faker
    -0.25
    -MM
    -0.24
    管çIJĨ模å¼ı
    -0.24
    out
    -0.24
    un
    -0.24
    POSITIVE LOGITS
    æĬĸ
    0.26
    ;charset
    0.25
    æĵ¾
    0.24
     Lightweight
    0.24
    anium
    0.24
    arkan
    0.23
     ìľĦíķ´ìĦľ
    0.23
    athers
    0.23
    Fully
    0.23
    ,msg
    0.23
    Activations Density 0.009%

    No Known Activations