© 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. 9538
    Prev
    Next
    INDEX
    Explanations

    main component or example

    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
    à°Ĺà±ģ
    -0.09
     Æ¡i
    -0.08
    æī¹åĩĨçļĦé¡¹çĽ®
    -0.08
    Ahead
    -0.08
    å¥½å£°éŁ³
    -0.08
    edException
    -0.08
    æľīä¸Ģä½į
    -0.08
    ä¸Ģè¯į
    -0.07
    icky
    -0.07
    oop
    -0.07
    POSITIVE LOGITS
    并ç»ĵåIJĪ
    0.09
    ï¼Į
    0.09
    èĢĮ以
    0.08
    è¿ĺæĺ¯ä»¥
    0.08
    è¿Ľè¡Į
    0.08
    æĪĸ以
    0.07
    ,
    0.07
    ØĮ
    0.07
    ç³»ç»Łè¿Ľè¡Į
    0.07
    èĢĮ对
    0.06
    Activations Density 0.018%

    No Known Activations