© 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. 40522
    Prev
    Next
    INDEX
    Explanations

    collect the terms

    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
    æĸ°åĬłåĿ¡
    -0.08
    achim
    -0.07
    ç¡®
    -0.07
     vrais
    -0.07
    اÙĨÙĬا
    -0.07
    对个人
    -0.07
    æ¯Ķè¾ĥé«ĺ
    -0.07
     sebebi
    -0.07
    تابع
    -0.07
    menes
    -0.07
    POSITIVE LOGITS
    ke
    0.06
    èĴĻ
    0.06
    ÂŃing
    0.06
    stig
    0.06
    ley
    0.06
    HAM
    0.06
    åıĪ好
    0.06
    l
    0.06
    æĭŃ
    0.06
    akar
    0.06
    Activations Density 0.035%

    No Known Activations