© 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. 39044
    Prev
    Next
    INDEX
    Explanations

    dissertation or study context

    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
    -0.07
    å±ħ
    -0.07
    adu
    -0.07
    onte
    -0.07
    è±
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.06
     compelled
    -0.06
    èĢģçīĮ
    -0.06
    atel
    -0.06
    éĥİ
    -0.06
    POSITIVE LOGITS
    thesis
    0.11
     thesis
    0.10
     CHAPTER
    0.10
     dissertation
    0.10
    æľ¬ç«ł
    0.09
     investigador
    0.09
     Chapter
    0.09
     Thesis
    0.09
    æľ¬çłĶ究
    0.09
     chapters
    0.09
    Activations Density 0.053%

    No Known Activations