© 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. 17755
    Prev
    Next
    INDEX
    Explanations

    followed by examples

    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
    iggers
    -0.07
    æĺ¯åŃ©åŃIJ
    -0.07
    è¿ĺæĺ¯æ²¡æľī
    -0.07
    ÑĢÑĭÑħ
    -0.07
    ä»Ģä¹Īæł·çļĦ
    -0.07
    æĿ¥ç¡®å®ļ
    -0.07
    ä»Ģä¹ĪåİŁåĽł
    -0.07
    çļĦåİŁåĽłä¹ĭä¸Ģ
    -0.06
    æĺ¯åŃ¦æł¡
    -0.06
    aris
    -0.06
    POSITIVE LOGITS
     lautet
    0.13
    æłĩåĩĨ为
    0.09
     correct
    0.08
    åħ¸åŀĭ
    0.08
    ä¾Ŀ次为
    0.08
    ylon
    0.08
    æŃ£ç¡®çļĦæĺ¯
    0.07
    æŃ£ç¡®çļĦ
    0.07
    _safe
    0.07
    oro
    0.07
    Activations Density 0.197%

    No Known Activations