© 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. 9419
    Prev
    Next
    INDEX
    Explanations

    EFF, News, Brian, You, P

    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
    屿
    -0.07
    Gran
    -0.07
    ¿
    -0.07
    weiler
    -0.07
    åĦ¿
    -0.07
    çļĦ人åĴĮ
    -0.06
    ¶
    -0.06
    ereum
    -0.06
    kking
    -0.06
    æĪijè¦ģæĬķè¯ī
    -0.06
    POSITIVE LOGITS
    ìĿĺ
    0.17
    ãģ®
    0.14
    çļĦåIJĮæŶ
    0.14
    çļĦä½ł
    0.13
    çļĦéĩį
    0.12
    çļĦéĢŁåº¦
    0.12
    çļĦ社ä¼ļ
    0.12
    çļĦè¿ĩç¨ĭä¸Ń
    0.12
    çļĦåѦçĶŁ
    0.12
    çļĦæł¸å¿ĥ
    0.12
    Activations Density 6.697%

    No Known Activations