© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56920
    Prev
    Next
    INDEX
    Explanations

    glucose, unemployed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ³
    -0.07
    's
    -0.06
    ãģ¨ãģĦãģĨ
    -0.06
    èµ°
    -0.06
     about
    -0.05
    ammel
    -0.05
    èĥ½æľī
    -0.05
     Fried
    -0.05
    زÙĬ
    -0.05
    inya
    -0.05
    POSITIVE LOGITS
    noch
    0.09
    wego
    0.09
    blia
    0.09
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.08
    çīĪæĿĥå±ŀäºİ
    0.08
     zbo
    0.08
    cão
    0.08
    éĩįæĿ¥
    0.08
     ÙĪاÙĦØ°ÙĬ
    0.08
    ×ķר×Ļ
    0.08
    Activations Density 0.037%

    No Known Activations