© 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. 3782
    Prev
    Next
    INDEX
    Explanations

    percentage, ratio, fraction

    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
    ypad
    -0.07
    spl
    -0.07
    å¦Ĥä½ķ解åĨ³
    -0.07
    æ±Ĥç²¾
    -0.07
     bulky
    -0.06
    æļĤè¡Į
    -0.06
    é¢ĨåľŁ
    -0.06
    æĺ¯åĶ¯ä¸Ģ
    -0.06
    ק×Ķ
    -0.06
    iar
    -0.06
    POSITIVE LOGITS
     ratios
    0.10
     ratio
    0.10
     Ratio
    0.09
     percentage
    0.09
    æ¯Ķçİĩ
    0.09
     fraction
    0.09
    ratio
    0.09
     Percentage
    0.09
    æ¯Ķä¾ĭ
    0.09
    çĻ¾åĪĨæ¯Ķ
    0.08
    Activations Density 0.019%

    No Known Activations