© 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. 151193
    Prev
    Next
    INDEX
    Explanations

    Code and imports

    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
    é£ŀ
    -0.31
    ä¸Ĭ游
    -0.26
    é£Ľ
    -0.26
    sett
    -0.26
    radi
    -0.25
    VML
    -0.25
    heed
    -0.25
     Fly
    -0.25
     migrated
    -0.25
     Kv
    -0.24
    POSITIVE LOGITS
    vron
    0.31
    ç»ıè´¸
    0.27
    交éĢļè¿IJè¾ĵ
    0.26
    å½¢å¼ı
    0.26
    pra
    0.26
    å¸Ĥåľºç»ıæµİ
    0.24
    exports
    0.24
    褴
    0.24
    .Basic
    0.24
    个交æĺĵ
    0.23
    Activations Density 0.122%

    No Known Activations