© 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. 23130
    Prev
    Next
    INDEX
    Explanations

    food and drink

    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
    åĽ½å¤ĸ
    -0.32
    licit
    -0.31
    åģĥ
    -0.31
    gles
    -0.28
    .fil
    -0.27
    欧ç¾İ
    -0.27
    æ¤į
    -0.26
    é¤Ĭ
    -0.26
    mail
    -0.26
    åħ»
    -0.26
    POSITIVE LOGITS
     cups
    0.37
     beverages
    0.37
    cup
    0.35
    饮æĸĻ
    0.35
     drink
    0.35
     beverage
    0.34
    åĸĿ
    0.33
    æĿ¯åŃIJ
    0.33
    drink
    0.32
    æĿ¯
    0.31
    Activations Density 0.009%

    No Known Activations