© 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. 24-TRANSCODER-HP
    7. 149188
    Prev
    Next
    INDEX
    Explanations

    typically

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     normally
    -0.27
    ad
    -0.27
    ä¸ĢèĪ¬äºº
    -0.27
     lur
    -0.26
    ä¸ĢèĪ¬
    -0.25
    è¿ĻæĶ¯
    -0.25
    ixa
    -0.25
    æĬĺ
    -0.25
    è¿Ļå¼ł
    -0.24
    ä¸ĢèĪ¬éĥ½æĺ¯
    -0.24
    POSITIVE LOGITS
    æĽ´å¥½çļĦ
    0.28
    çĭ¬ä¸Ģ
    0.25
    å¹³çŃī
    0.25
    ctor
    0.24
    symbols
    0.24
     spons
    0.24
    endants
    0.24
    protocols
    0.23
    çļĦæľĭåıĭ
    0.23
    .getLocal
    0.23
    Activations Density 0.294%

    No Known Activations