© 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. 58407
    Prev
    Next
    INDEX
    Explanations

    clarification questions

    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
    åİŁåĽłå°±æĺ¯
    -0.08
    zial
    -0.07
    æľĢç»Ī以
    -0.07
    æĹ©æĹ¥åº·å¤į
    -0.07
    birthdate
    -0.07
    ,ev
    -0.07
    ä½łä¸Ģå®ļè¦ģ
    -0.07
    edur
    -0.07
    tah
    -0.07
     ë°ĺëĵľìĭľ
    -0.07
    POSITIVE LOGITS
    ä¼¼ä¹İ
    0.17
    好åĥı
    0.16
     seems
    0.15
     seem
    0.15
    ä¼¼ä¹İåľ¨
    0.14
    ä¼¼ä¹İä¹Ł
    0.14
    ä¼¼ä¹İæĺ¯
    0.13
    éļ¾éģĵ
    0.13
    好åĥıåľ¨
    0.13
     seemed
    0.13
    Activations Density 3.373%

    No Known Activations