© 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. 20878
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
    ä½ķå¤Ħ
    -0.09
     \`
    -0.09
    æѤå¤Ħ
    -0.08
    ĻĤ
    -0.08
    ä½ķç§į
    -0.08
    æĸ¹æīį
    -0.07
    æĸ¹åı¯
    -0.07
    æѤç§į
    -0.07
    sono
    -0.07
    æĹłçĶ¨
    -0.07
    POSITIVE LOGITS
    红红çļĦ
    0.08
    æĺ¯è¿Ļæł·çļĦ
    0.07
    ç»ĻæĪij们çļĦ
    0.07
    æľīåĵªäºĽåij¢
    0.07
    主æŨ
    0.07
     pretty
    0.07
    ç»Ļ大家åĪĨ享
    0.07
     polega
    0.07
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    0.07
    è¯Ŀ说
    0.06
    Activations Density 0.001%

    No Known Activations