© 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. 47998
    Prev
    Next
    INDEX
    Explanations

    fragile, sensitive, unstable, reactive, short, brittle

    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
    åĨ·æ·¡
    -0.07
    åĨ·æ¼ł
    -0.07
     independent
    -0.07
    ä¸įä¸Ģå®ļæĺ¯
    -0.07
    ä¸įåĩı
    -0.06
    硬
    -0.06
    ä¸įæĭĺ
    -0.06
    ä¸įä¸Ģå®ļ
    -0.06
    æ·¡å®ļ
    -0.06
    åĨ·éĿĻ
    -0.06
    POSITIVE LOGITS
     fragile
    0.14
    èĦĨå¼±çļĦ
    0.14
    åıªèĥ½åľ¨
    0.13
     sensitive
    0.12
    -sensitive
    0.11
    èĦĨå¼±
    0.11
    ä¸įèĥ½åľ¨
    0.11
     sensitivity
    0.11
    æķıæĦŁæĢ§
    0.11
     perish
    0.11
    Activations Density 0.091%

    No Known Activations