© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16901
    Prev
    Next
    INDEX
    Explanations

    true/false conditions

    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
    äºĨåIJĹ
    -0.08
    æĸ¹æ³ķæĿ¥
    -0.08
     Xo
    -0.07
    èĭ¥éĿŀ
    -0.07
    çĤ¹åIJİ
    -0.07
    为主çļĦ
    -0.07
    以éĢĤåºĶ
    -0.07
    yton
    -0.07
    EAN
    -0.07
    OOD
    -0.07
    POSITIVE LOGITS
     slightest
    0.08
    æĪĸèĢħæľī
    0.08
    æĿ¡ä»¶æĺ¯
    0.07
     otherwise
    0.07
    æĪĸåľ¨
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
    æĢ§æĪĸ
    0.07
     ÙĪÙĤبÙĦ
    0.07
    ié
    0.07
    vice
    0.07
    Activations Density 0.163%

    No Known Activations