© 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. 40289
    Prev
    Next
    INDEX
    Explanations

    Kickstarter campaign or partnership

    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
    éĥ¨åĪĨç»ĦæĪIJ
    -0.09
    ergestellt
    -0.08
    wed
    -0.07
    imt
    -0.07
    ENCY
    -0.07
    ä¸įèµ·æĿ¥
    -0.07
    è·Łèĩªå·±
    -0.07
    thers
    -0.07
    æĢĴäºĨ
    -0.07
    éļ¾çľĭ
    -0.07
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.14
    èĢĮæĿ¥çļĦ
    0.11
    çļĦè¿ĺæľī
    0.10
    为ä¸Ģä½ĵçļĦ
    0.09
    äºİä¸Ģä½ĵçļĦ
    0.09
    注æĦıçļĦæĺ¯
    0.09
    èĢĮ产çĶŁçļĦ
    0.09
    好å¤ĦçļĦ
    0.08
    éķ¿å¤§çļĦ
    0.08
    为主é¢ĺçļĦ
    0.08
    Activations Density 0.120%

    No Known Activations