© 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. 151236
    Prev
    Next
    INDEX
    Explanations

    Unstructured text

    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
    ãĥ³ãĤ°
    -0.28
    steller
    -0.27
    оÑģÑĮ
    -0.26
    *sp
    -0.25
    .transitions
    -0.25
    yster
    -0.25
    ingt
    -0.24
    é»ŀ
    -0.24
    qid
    -0.24
     oversh
    -0.23
    POSITIVE LOGITS
    è¿ĻæĿ¡
    0.33
    ä¹Łåı¯
    0.31
     reading
    0.28
     locus
    0.26
    éĺħ读
    0.26
    ä¹Łåı¯ä»¥
    0.26
     Parks
    0.25
    ä¸ĩ个
    0.25
    åľ¨è¿Ļ
    0.25
     Reading
    0.25
    Activations Density 0.122%

    No Known Activations