© 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. 20-TRANSCODER-HP
    7. 107407
    Prev
    Next
    INDEX
    Explanations

    formatting (code/writing)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Łåıªèĥ½
    -0.39
     seulement
    -0.29
    ãģłãģijãģ§ãģªãģı
    -0.29
    ä¸Ģ群人
    -0.28
    ãģĹãģĭãĤĤ
    -0.28
    åıªæĺ¯ä¸ºäºĨ
    -0.28
    ç´§æİ¥çĿĢ
    -0.27
    èĢĮéĿŀ
    -0.27
    éĤ£ç§į
    -0.27
    .slim
    -0.27
    POSITIVE LOGITS
    çļĦ身份
    0.27
    аниÑĨ
    0.27
    .SO
    0.26
     SO
    0.26
    à¹Īว
    0.25
     doubt
    0.25
    çļĦåĪ°æĿ¥
    0.24
    çļĦåŃĺåľ¨
    0.24
    ’s
    0.24
     JO
    0.24
    Activations Density 67.047%

    No Known Activations