© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    coefficients and bounds

    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
    íĥĿ
    -0.07
    ander
    -0.07
    odium
    -0.07
    ì¼ĵ
    -0.07
    è·µè¸ı
    -0.06
    ASSES
    -0.06
    ulik
    -0.06
    çļ®éŀĭ
    -0.06
    æĸ°å¨ĺ
    -0.06
    ä½İ端
    -0.06
    POSITIVE LOGITS
     coefficients
    0.09
     коÑįÑĦÑĦиÑĨи
    0.08
    åĴĮå¹³
    0.08
    coeff
    0.08
    ç³»æķ°
    0.08
     coefficient
    0.08
    yks
    0.08
    nock
    0.08
     pär
    0.07
    /npm
    0.07
    Activations Density 0.009%

    No Known Activations