© 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. 14414
    Prev
    Next
    INDEX
    Explanations

    user id or coupon id

    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
    ä¹ĥ
    -0.10
    å·²çĦ¶
    -0.09
    åIJĥäºĨ
    -0.09
    åı¯ä¾Ľ
    -0.08
    çŁ¥éģĵäºĨ
    -0.08
    æĺİç¡®äºĨ
    -0.08
    боÑİ
    -0.08
    ç»ıè¿ĩäºĨ
    -0.08
    æķ´çIJĨçļĦ
    -0.08
    ucc
    -0.08
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.09
    ä»İéĤ£
    0.08
    èĢĮä¸Ķè¿ĺæĺ¯
    0.08
    ä¸įæĺ¯åIJĹ
    0.08
    è¿Ľè¡Į
    0.07
     use
    0.07
    çļĦéĥ½æĺ¯
    0.07
    顾åıĬ
    0.07
    çļĦä¸įæĺ¯
    0.07
    åħ³æ³¨åĴĮ
    0.07
    Activations Density 0.009%

    No Known Activations