© 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. 12842
    Prev
    Next
    INDEX
    Explanations

    indicating something that implies

    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
    çļĦæľīåħ³
    -0.08
    asin
    -0.07
    é¸¡æ¯Ľ
    -0.07
    สุวรรà¸ĵ
    -0.07
    åĸľæĢĴåĵĢä¹IJ
    -0.07
    uvé
    -0.07
    ä¹IJä¹İ
    -0.07
    æĢİä¹Ī说
    -0.07
    resentation
    -0.07
    adder
    -0.07
    POSITIVE LOGITS
     implies
    0.09
    强è°ĥäºĨ
    0.08
    强è°ĥçļĦæĺ¯
    0.08
    çļĦæĦıæĢĿ
    0.08
    æĦıæĢĿæĺ¯
    0.08
    ä¸Ģç§į
    0.08
    æĮĩçļĦæĺ¯
    0.08
    æĦıåij³çĿĢ
    0.08
    ines
    0.08
    çļĦæĦıæĢĿæĺ¯
    0.07
    Activations Density 0.022%

    No Known Activations