© 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. 60958
    Prev
    Next
    INDEX
    Explanations

    book edition

    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°æµªç½ij
    -0.08
    dej
    -0.07
    dar
    -0.07
    ä¸Ģéĺµ
    -0.07
    acco
    -0.07
    achie
    -0.07
    »
    -0.07
    tej
    -0.07
    ä¸Ģçķª
    -0.07
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    POSITIVE LOGITS
    æŁ»
    0.08
    çīĪçļĦ
    0.08
    лÑıн
    0.07
    ãĤĴè¿İ
    0.07
    ity
    0.07
    ureau
    0.07
    ITY
    0.07
    以æĿ¥çļĦ
    0.07
    egis
    0.07
     versions
    0.06
    Activations Density 0.053%

    No Known Activations