© 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. 32-TRANSCODER-HP
    7. 41108
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    详ç»Ĩ
    -0.35
    详ç»ĨçļĦ
    -0.33
    enance
    -0.30
     commonplace
    -0.27
    åijĪçİ°åĩº
    -0.26
    etas
    -0.25
     resin
    -0.25
    èĽĩ
    -0.25
     fragile
    -0.25
    åijĪçİ°
    -0.25
    POSITIVE LOGITS
    .preference
    0.33
    é¢Ħæ¡Ī
    0.32
    æĢĿ
    0.31
    Plan
    0.27
    reet
    0.27
     Plan
    0.25
    æĥ³
    0.25
    沧
    0.25
    REAM
    0.24
    usat
    0.24
    Activations Density 0.002%

    No Known Activations