© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    rise in

    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
    ness
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    urop
    -0.08
    åĩºèº«çļĦ
    -0.08
    inee
    -0.08
    çļĦ好åĿı
    -0.08
    é£İéľľ
    -0.08
    æİīäºĨ
    -0.07
    è½»éĩį
    -0.07
    ihin
    -0.07
    POSITIVE LOGITS
    à¹Ģรืà¹Īà¸Ńยà¹Ĩ
    0.11
    /down
    0.10
     pesat
    0.10
    ä¸ĢåĢį
    0.09
    /de
    0.09
    èµ·æĿ¥çļĦ
    0.09
     trÆ°á»Łng
    0.09
    åĬ¿å¤´
    0.08
    åİĭåĻ¨
    0.08
    å¹ħ度
    0.08
    Activations Density 0.161%

    No Known Activations