© 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. 13236
    Prev
    Next
    INDEX
    Explanations

    required for password

    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
    aliz
    -0.09
    ×Ļ×Ļ
    -0.09
    æıIJåĢ¡
    -0.08
    ä¾
    -0.07
     rew
    -0.07
    æĪijåIJ¬
    -0.07
    اÙĪر
    -0.07
    ä¹Łç§°
    -0.07
    olie
    -0.07
    åıªè¦ģæĺ¯
    -0.07
    POSITIVE LOGITS
    åıªçŁ¥éģĵ
    0.11
    çŁ¥
    0.10
    çŁ¥éģĵ
    0.09
    æľªçŁ¥çļĦ
    0.09
    info
    0.08
    è¿ĻäºĽä¿¡æģ¯
    0.08
    æľªçŁ¥
    0.08
     know
    0.08
    çŁ¥éģĵçļĦ
    0.08
    æĽ´å¤ļä¿¡æģ¯
    0.08
    Activations Density 0.014%

    No Known Activations