© 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. 151377
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
    ç®´
    -0.27
    æ°ijæĦı
    -0.27
    å®°
    -0.25
    رات
    -0.24
    eso
    -0.24
     waypoints
    -0.23
    essages
    -0.23
    åĩłæ¬¡
    -0.23
    åIJijå¤ĸ
    -0.23
    å¤ĸåľ°
    -0.22
    POSITIVE LOGITS
    oland
    0.26
     fiber
    0.25
    uje
    0.24
    çļĦæłĩåĩĨ
    0.24
    åĬ¨çĶŁæĪIJ
    0.24
    enne
    0.24
    iber
    0.23
    ARC
    0.23
    sert
    0.23
    isce
    0.23
    Activations Density 0.073%

    No Known Activations