© 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. 11559
    Prev
    Next
    INDEX
    Explanations

    untreated, unprotected, unchecked states

    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
    èĬĬ
    -0.08
    ä¸įä¼ļåĨį
    -0.07
     abst
    -0.07
    åĨįä¹Łä¸įçĶ¨
    -0.07
    åĨįä¹Ł
    -0.07
    leigh
    -0.07
    çĽ¸å¯¹ç¨³å®ļ
    -0.07
    rene
    -0.07
    è¿Ļæł·å°±åı¯ä»¥
    -0.06
    è°ģ说
    -0.06
    POSITIVE LOGITS
     unchecked
    0.13
    æĪĸæľª
    0.12
    æľªç»ı
    0.10
    缺ä¹ı
    0.10
    æĶ¾ä»»
    0.09
    ãģ¾ãģ¾
    0.09
    ä¸įåĬł
    0.09
     untreated
    0.09
    没æľīå¾ĹåĪ°
    0.09
     unprotected
    0.09
    Activations Density 0.179%

    No Known Activations