© 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. 12-TRANSCODER-HP
    7. 23007
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    張貼
    -0.28
     reversal
    -0.27
    é³Ģ
    -0.27
     oppos
    -0.27
    (""
    -0.26
     opposing
    -0.26
     reversed
    -0.26
    adel
    -0.26
    _reverse
    -0.25
     ×ĵ×ķ
    -0.25
    POSITIVE LOGITS
    ixin
    0.29
    .executeQuery
    0.26
    æݬ
    0.26
     watering
    0.26
     FETCH
    0.25
    æµħ
    0.24
     Bez
    0.24
    getExtension
    0.24
    rus
    0.24
     fetched
    0.24
    Activations Density 0.003%

    No Known Activations