© 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. 64338
    Prev
    Next
    INDEX
    Explanations

    programming guidelines

    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
    æľīä½Ļ
    -0.08
    缸åħ³èµĦ讯
    -0.08
     wah
    -0.08
    yleft
    -0.07
    å®īåħ¨éĹ®é¢ĺ
    -0.07
    .solution
    -0.07
    oooooooo
    -0.06
    åĩºå¸Ńä¼ļè®®
    -0.06
    .twig
    -0.06
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.06
    POSITIVE LOGITS
    æīĭåĨĮ
    0.09
    æĮĩå¼ķ
    0.08
    å®ĪåĪĻ
    0.08
    æĮĩåįĹ
    0.08
    æļĤè¡Į
    0.08
    ç»ĨåĪĻ
    0.08
    è§Ħç¨ĭ
    0.07
    åĽ¾è°±
    0.07
    çĶ¨ä¹¦
    0.07
    é¢ĺåºĵ
    0.07
    Activations Density 0.061%

    No Known Activations