© 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. 28969
    Prev
    Next
    INDEX
    Explanations

    quantum theory, physicists, invention

    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
    ç¾İ好çļĦæľªæĿ¥
    -0.08
     perse
    -0.08
     Pompeo
    -0.08
    çĴ°çIJĥ
    -0.07
    룡
    -0.07
     mạo
    -0.07
    ICHE
    -0.07
    åĮĸæĪIJ
    -0.07
     оÑģнование
    -0.07
     Flames
    -0.07
    POSITIVE LOGITS
    æľīäºĽäºĭ
    0.07
    诧
    0.07
    ä¸»å¼ł
    0.07
    Shot
    0.07
    ubles
    0.07
     Sho
    0.07
    åĶ¯
    0.07
     probabil
    0.06
     randomized
    0.06
    vasive
    0.06
    Activations Density 0.010%

    No Known Activations