© 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. 40194
    Prev
    Next
    INDEX
    Explanations

    providing alternatives

    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
    ied
    -0.09
    è¿Ļæł·å°±åı¯ä»¥
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
    è¿Ļæł·åı¯ä»¥
    -0.07
    åĩĨå¤ĩ好äºĨåIJĹ
    -0.07
    çĦ¶åIJİçĤ¹åĩ»
    -0.07
    zil
    -0.07
    esy
    -0.07
    ä½Ĩåıªè¦ģ
    -0.07
    POSITIVE LOGITS
    thon
    0.11
    åħ¶ä»ĸæĸ¹å¼ı
    0.10
    vrier
    0.09
    ients
    0.09
     اÛĮÙĨÚ©Ùĩ
    0.08
    çļĦè¯Ŀ
    0.08
    baugh
    0.08
    phans
    0.08
    åħ¶å®ĥ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    Activations Density 0.004%

    No Known Activations