© 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. 3935
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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
    ئÛĮ
    -0.06
    ä½ij
    -0.06
    çļĦå·¥ä½ľä¸Ń
    -0.06
    aders
    -0.06
    èµ·äºļ
    -0.06
    åİ»å¾Ģ
    -0.06
    koord
    -0.06
    æĥķ
    -0.06
    ader
    -0.06
    çĢij
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.08
    两åѦä¸Ģåģļ
    0.08
     Douglas
    0.08
    èĬ±çµ®
    0.07
    __$
    0.07
    å¾Ĺåħ¶
    0.07
     //-
    0.07
     fác
    0.07
    ,//
    0.07
    åIJĦç§įåIJĦæł·
    0.07
    Activations Density 0.055%

    No Known Activations