© 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. 4480
    Prev
    Next
    INDEX
    Explanations

    association, stroke, vessels, DNA, message, code

    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
    /../
    -0.08
    å¼Ħ
    -0.07
    åľ¨ç¾İ
    -0.07
     alone
    -0.07
    æ¶Īæŀģ
    -0.07
    .Microsoft
    -0.07
    urÄĥ
    -0.07
    æĬĹ
    -0.06
    å©¿
    -0.06
     seuls
    -0.06
    POSITIVE LOGITS
    ç»ıéªĮçļĦ
    0.08
    ious
    0.08
    ese
    0.08
    ç»ıéªĮ丰å¯ĮçļĦ
    0.08
     nearby
    0.07
    ç»ıéªĮ
    0.07
    ibra
    0.07
    ç»ıéªĮåĴĮ
    0.07
    ç»ıéªĮåĪĨ享
    0.07
    çīĮåŃIJçļĦ
    0.07
    Activations Density 0.104%

    No Known Activations