© 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. 23768
    Prev
    Next
    INDEX
    Explanations

    as

    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
    æĺĻ
    -0.28
    æ·ĭ
    -0.27
    å¨ĺ家
    -0.26
     appropriations
    -0.26
    earn
    -0.25
     Baths
    -0.24
    /array
    -0.24
     prominently
    -0.24
     kop
    -0.24
     earnings
    -0.23
    POSITIVE LOGITS
    .globalData
    0.28
     mee
    0.28
     Passport
    0.26
    Physical
    0.26
     Physical
    0.25
    oun
    0.25
    产åĩº
    0.25
    æ°ij
    0.24
     heavier
    0.24
     Seriously
    0.24
    Activations Density 0.013%

    No Known Activations