© 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. 10721
    Prev
    Next
    INDEX
    Explanations

    correct or right

    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
    éĥijéĩį声æĺİ
    -0.09
    è¿Ļæĺ¯çĶ±äºİ
    -0.08
    iets
    -0.08
    æł¹æľ¬æĹłæ³ķ
    -0.08
    æł¹æľ¬ä¸į
    -0.07
    kol
    -0.07
    æł¹æľ¬å°±ä¸į
    -0.07
    ยาย
    -0.07
    vince
    -0.07
    æľ¬ç¤¾
    -0.07
    POSITIVE LOGITS
    æĺ¯æŃ£ç¡®çļĦ
    0.10
     correctness
    0.09
    æĺ¯å¯¹çļĦ
    0.08
    æĹłè¯¯
    0.08
    没éĶĻ
    0.08
    没æľīéĹ®é¢ĺ
    0.08
     correct
    0.08
    æ²ĴéĮ¯
    0.07
     correcto
    0.07
    æĺ¯åIJ¦æŃ£ç¡®
    0.07
    Activations Density 0.008%

    No Known Activations