© 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. 30-TRANSCODER-HP
    7. 94968
    Prev
    Next
    INDEX
    Explanations

    genealogy and family history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     redo
    -0.27
    ãĤĴæİ¢ãģĻ
    -0.26
     quit
    -0.26
    çĶ¨èĩªå·±çļĦ
    -0.25
     Playoff
    -0.25
    iami
    -0.25
     foreseeable
    -0.24
    .promise
    -0.24
    dea
    -0.23
     setResult
    -0.23
    POSITIVE LOGITS
    积
    0.28
    stellung
    0.25
    å¢Ļ
    0.25
    åĻªéŁ³
    0.25
    线
    0.25
    空çĻ½
    0.25
    acen
    0.25
    agens
    0.24
    è¿Ń
    0.24
    .Generated
    0.24
    Activations Density 0.102%

    No Known Activations