© 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. 19886
    Prev
    Next
    INDEX
    Explanations

    polite questions or statements

    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
    éĹ®é¢ĺæŶ
    -0.09
    å·¥ä½ľæŶ
    -0.09
    æķħèĢĮ
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    ç»ĻåŃ©åŃIJ们
    -0.08
     λοι
    -0.08
    Ïģιν
    -0.08
    IfNeeded
    -0.08
    为åİŁåĪĻ
    -0.08
    iges
    -0.08
    POSITIVE LOGITS
    ãģĿãĤĮãģ¯
    0.10
    缸åºĶçļĦ
    0.09
    ãģĿãĤĮãĤĴ
    0.09
    éĤ£
    0.08
    ãģĿãĤĮãĤĤ
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    å°±åĪ«
    0.08
     Äijó
    0.08
     Ø¢ÙĨ
    0.08
     thereof
    0.08
    Activations Density 0.462%

    No Known Activations