© 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. 58249
    Prev
    Next
    INDEX
    Explanations

    c++

    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
    iesel
    -0.08
    å¥½å¥½åľ°
    -0.07
    luv
    -0.07
    éħİ
    -0.07
    vinc
    -0.07
    ãģĹãģŁãģĵãģ¨
    -0.07
    ned
    -0.07
    outers
    -0.07
    enders
    -0.07
    oked
    -0.07
    POSITIVE LOGITS
    éħ¿
    0.07
    atta
    0.07
    æĻĵ举
    0.07
    avat
    0.07
    umba
    0.06
    ensem
    0.06
    Ñĥма
    0.06
    Unsafe
    0.06
    ä¹İ
    0.06
    Coeff
    0.06
    Activations Density 0.001%

    No Known Activations