© 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. 40785
    Prev
    Next
    INDEX
    Explanations

    cell damage

    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
    adow
    -0.08
    añ
    -0.08
    åĬłæĭ¿å¤§
    -0.07
    eck
    -0.07
    å·¥ç¨ĭçŃī
    -0.07
    å¹´äºĨ
    -0.07
    çİĭä¹ĭ
    -0.07
    ÙĬÙĦÙĬØ©
    -0.07
    个ä¸ĵä¸ļ
    -0.07
    æīĵæĿ¥
    -0.07
    POSITIVE LOGITS
    人家
    0.09
    éĹ´çĽĺ
    0.06
    们
    0.06
    浩
    0.06
    å¾®
    0.06
    æĸ¹æĸ¹éĿ¢
    0.06
    à¹Į
    0.06
    ãģ¡ãĤĥ
    0.06
    �
    0.06
    çļĦè¿Ļä¸Ģ
    0.06
    Activations Density 0.014%

    No Known Activations