© 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. 55629
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by a comma or conjunction

    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
    моÑĢа
    -0.11
    æľ¬èº«
    -0.09
    被人
    -0.08
     ourselves
    -0.08
     باÙĦÙĨسبة
    -0.07
    æĪijèĩªå·±
    -0.07
    é£İåIJ¹è¿ĩ
    -0.07
    ä¸İ人
    -0.07
    人被
    -0.07
    ÑģÑı
    -0.07
    POSITIVE LOGITS
    åĴĮèĩªå·±
    0.12
    è·Łèĩªå·±
    0.10
    æĺ¯åħ¶
    0.10
    è¦ģæ±Ĥåħ¶
    0.10
    æ¯Ķèĩªå·±
    0.09
    ä¸İèĩªå·±
    0.09
    åĴĮèĩªå·±çļĦ
    0.09
    æĺ¯èĩªå·±çļĦ
    0.08
    为åħ¶
    0.08
    åIJijåħ¶
    0.08
    Activations Density 0.453%

    No Known Activations