© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96646
    Prev
    Next
    INDEX
    Explanations

    Diseases and code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    side
    -0.35
    -side
    -0.29
    roach
    -0.28
    سÙĥ
    -0.28
     side
    -0.28
    bah
    -0.27
    sla
    -0.26
    é«ĺè´µ
    -0.26
    case
    -0.25
    صرÙģ
    -0.25
    POSITIVE LOGITS
     Ness
    0.27
     propTypes
    0.25
    ARY
    0.25
    天èĬ±æĿ¿
    0.25
     futuro
    0.24
    åīįæıIJæĺ¯
    0.24
    Ymd
    0.24
    nev
    0.24
     kidding
    0.23
    nces
    0.23
    Activations Density 0.002%

    No Known Activations