© 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. 149191
    Prev
    Next
    INDEX
    Explanations

    Code and legal snippets

    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
    ä»ĺ
    -0.26
    æıIJä¾Ľä¼ĺè´¨
    -0.25
    åľ¨æĹ¥æľ¬
    -0.25
     spect
    -0.24
    ä»ĺãģij
    -0.24
    ocular
    -0.24
    ç»ıèIJ¥æ´»åĬ¨
    -0.23
     Ment
    -0.23
    erty
    -0.23
     sell
    -0.23
    POSITIVE LOGITS
    illions
    0.29
    å¼ķæĵİ
    0.29
     Engine
    0.28
     belt
    0.27
    åı¥
    0.27
    ityEngine
    0.27
    oyal
    0.27
    _ENGINE
    0.27
    é¢ĺ主
    0.27
    Sentence
    0.26
    Activations Density 0.157%

    No Known Activations