© 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. 22376
    Prev
    Next
    INDEX
    Explanations

    ratios and proportions

    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
    rick
    -0.09
    秸
    -0.09
    è§ĨçĤ¹
    -0.08
    awang
    -0.08
    eke
    -0.08
    ohlen
    -0.08
    ç´łé£Ł
    -0.08
    оÑģÑĤей
    -0.08
    koh
    -0.08
    ëĭIJ
    -0.08
    POSITIVE LOGITS
     ratio
    0.08
    ä¸Ģæ¯Ķ
    0.08
    ï¸İ
    0.08
     ratios
    0.07
     Ratio
    0.07
    ç½ijåIJ§
    0.07
    ł
    0.07
    æ¯Ķä¾ĭ为
    0.06
    iful
    0.06
    æ¯Ķä¾ĭ
    0.06
    Activations Density 0.021%

    No Known Activations