© 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. 23-TRANSCODER-HP
    7. 23548
    Prev
    Next
    INDEX
    Explanations

    code/math/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     full
    -0.38
     final
    -0.35
    æľ«ç«¯
    -0.35
    ç»Ī
    -0.34
    èĮĥåĽ´
    -0.33
    æľĢåIJİ
    -0.32
    ç»ĪçĤ¹
    -0.32
    满
    -0.32
    æľĢåIJİä¸Ģ
    -0.32
     Finals
    -0.32
    POSITIVE LOGITS
     indefinitely
    0.33
    inf
    0.32
    âĪŀ
    0.32
     Unlimited
    0.30
     infinitely
    0.29
     Inf
    0.29
     inf
    0.29
     infinite
    0.29
    æĹłç©·
    0.27
    oub
    0.27
    Activations Density 0.004%

    No Known Activations