© 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. 24446
    Prev
    Next
    INDEX
    Explanations

    investigation results showed

    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
    -0.10
    åįłæ¯Ķ
    -0.09
    æĬĬæݧ
    -0.09
    -0.09
    -0.09
    è¿IJèIJ¥åķĨ
    -0.09
    çļĦéĤ£ä¸ĢåĪ»
    -0.09
    仪å¼ıæĦŁ
    -0.09
    æłĩéħį
    -0.09
    æĭ¥åłµ
    -0.08
    POSITIVE LOGITS
    象
    0.08
    åĴĮæľīåħ³
    0.08
    æIJŀ好
    0.08
    åIJĦç§įä¸įåIJĮçļĦ
    0.08
     USSR
    0.07
    ç´§ç´§åľ°
    0.07
    æĢİæł·
    0.07
    åıĬæľīåħ³
    0.07
    ä½ľ
    0.07
    被人们
    0.07
    Activations Density 0.050%

    No Known Activations