© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    locations and areas

    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
    åIJĦçľģ
    -0.07
    ä¹ĭæīĭ
    -0.07
    aky
    -0.06
     whatever
    -0.06
    æľ¬åĽ½
    -0.06
     Kraj
    -0.06
    ä¸į失
    -0.06
    æĪIJå¥Ĺ
    -0.06
    åĥıæĪij
    -0.06
    éĤ£ç§į
    -0.06
    POSITIVE LOGITS
    åıĬåij¨è¾¹
    0.09
    è¯ºåŁº
    0.09
     area
    0.09
    éĿ¢ç§¯çº¦
    0.09
    åĮºåŁŁåĨħ
    0.08
     presently
    0.08
     ehemaligen
    0.08
    area
    0.08
    æŶèĩ³ä»Ĭ
    0.08
    鼶æĺŁ
    0.08
    Activations Density 0.611%

    No Known Activations