© 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. 62069
    Prev
    Next
    INDEX
    Explanations

    asking for help or providing answers

    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
    ntl
    -0.08
    گذ
    -0.08
    rani
    -0.08
    "url
    -0.07
    nger
    -0.07
     rooting
    -0.07
    [target
    -0.07
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    æķĻèĤ²æĺ¯
    -0.07
    说äºĨç®Ĺ
    -0.07
    POSITIVE LOGITS
    ovice
    0.07
    éĻ
    0.07
    åľ¨è¿Ļæł·çļĦ
    0.07
     polis
    0.07
    æīĵäºĨ个
    0.07
    åļ
    0.07
    å±¥
    0.06
    iril
    0.06
     Prob
    0.06
    inline
    0.06
    Activations Density 0.001%

    No Known Activations