© 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. 12658
    Prev
    Next
    INDEX
    Explanations

    using ... off

    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
    åIJĴ
    -0.08
    ÑĥмÑĭ
    -0.07
    æľ¬ç¤¾
    -0.07
     thanks
    -0.07
     grazie
    -0.07
    ?page
    -0.06
    çľĭåİ»
    -0.06
    λεκ
    -0.06
    åªĽ
    -0.06
    æĿ¥æĦĪ
    -0.06
    POSITIVE LOGITS
     Terl
    0.08
    å¿ħé¡»åĿļæĮģ
    0.08
    åĿļæĮģ
    0.08
    abda
    0.08
    太å¤ļ
    0.07
    è¿ĩæĹ©
    0.07
    abri
    0.07
    太
    0.07
    太好
    0.07
    æĪijä¸Ģå®ļè¦ģ
    0.07
    Activations Density 0.034%

    No Known Activations