© 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. 10039
    Prev
    Next
    INDEX
    Explanations

    one or second format

    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
    èĥĮæĻ¯çļĦ
    -0.07
    æĸ°æŃĮ
    -0.07
    HeaderValue
    -0.07
    AGON
    -0.06
    æIJŃ建
    -0.06
    æIJŃ
    -0.06
    èĥĮæĻ¯
    -0.06
    жай
    -0.06
    åĸľ
    -0.06
     appropri
    -0.06
    POSITIVE LOGITS
    æĹłæĿ¡ä»¶
    0.08
    ä»»ä½ķä¸Ģç§į
    0.08
    ä»»ä½ķä¿Ŀè¯ģ
    0.08
    äºĴ缸
    0.08
    èĽĻ
    0.08
     داشتÙĨ
    0.08
    转æį¢ä¸º
    0.08
     Manifest
    0.07
    baugh
    0.07
    ToF
    0.07
    Activations Density 0.007%

    No Known Activations