© 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. 26878
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations

    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
    ophie
    -0.07
    umbing
    -0.06
    æıIJ示
    -0.06
    æĤ¨åı¯èĥ½
    -0.06
    å°Ĩ该
    -0.06
    ild
    -0.06
    ibat
    -0.06
    å½ĵãģŁãĤĬ
    -0.06
    poon
    -0.06
    è¿Ļåı¯èĥ½æĺ¯
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģç§į
    0.10
    è¿Ļä¸ľè¥¿
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    æĪijçĪ±ä½ł
    0.08
    ä¸įæĺ¯ä»Ģä¹Ī
    0.08
    çļĦå®ļä¹ī
    0.08
    ç»Ļ人çļĦ
    0.08
    ç»Ļ人们
    0.07
    åıĪåIJį
    0.07
    带ç»ĻæĪij们
    0.07
    Activations Density 0.034%

    No Known Activations