© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11928
    Prev
    Next
    INDEX
    Explanations

    volume and area measurements

    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
     blinking
    -0.07
    æ·¬
    -0.07
     Blink
    -0.07
    æĸ©
    -0.07
    çĹħæĥħåĪĨæŀIJ
    -0.07
    kev
    -0.07
    è¾ķ
    -0.07
    éĴ®
    -0.06
    ä¸įé½IJ
    -0.06
     Mint
    -0.06
    POSITIVE LOGITS
    éĿ¢ç§¯
    0.12
    éĿ¢ç§¯çļĦ
    0.11
    æĢ»éĿ¢ç§¯
    0.11
    çļĦéĿ¢ç§¯
    0.11
    éĿ¢ç©į
    0.10
     плоÑīадÑĮ
    0.10
    ä½ĵ积
    0.10
     area
    0.10
    表éĿ¢ç§¯
    0.09
    Area
    0.09
    Activations Density 0.010%

    No Known Activations