© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    defining a subgenre or type

    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
     Nobel
    -0.07
    çļĵ
    -0.07
    igg
    -0.07
    æĽ³
    -0.07
     famous
    -0.07
    å®ŀåľ¨æĺ¯å¤ª
    -0.07
    貫
    -0.07
    太åı¤
    -0.07
    è´¯
    -0.06
    ä¸ĥ大
    -0.06
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.13
    æ¯ĶæĻ®éĢļ
    0.13
    ä¸İæĻ®éĢļ
    0.10
     inherits
    0.09
    åĴĮæĻ®éĢļ
    0.08
    heber
    0.08
    åĮºåĪ«äºİ
    0.08
     presumably
    0.08
    çŃīçī¹æ®Ĭ
    0.08
    ç»ĵåIJĪäºĨ
    0.08
    Activations Density 0.420%

    No Known Activations