© 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. 57013
    Prev
    Next
    INDEX
    Explanations

    building or item description

    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
    ä½ķåħ¶
    -0.08
    æĹ¥åıijå¸ĥ
    -0.08
    å¿ħæľī
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    utions
    -0.07
    лов
    -0.07
    è¾Ħ
    -0.07
    itched
    -0.07
    èİ«åIJįåħ¶å¦Ļ
    -0.06
    åģļ强
    -0.06
    POSITIVE LOGITS
    è¦ģæĺ¯
    0.08
    æĪĸæĺ¯
    0.08
    è¦ģçŁ¥éģĵ
    0.08
     perk
    0.08
    æĪĸèĢħæĺ¯
    0.07
     tese
    0.07
    æĦıæĢĿ
    0.07
    å¾ĹåĩºçļĦ
    0.07
     nowadays
    0.07
    æĿ¥åIJ§
    0.07
    Activations Density 0.215%

    No Known Activations