© 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. 15868
    Prev
    Next
    INDEX
    Explanations

    seasons, regions, numbers, code

    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
    attery
    -0.08
    å¾Ĺèµ·
    -0.08
    igor
    -0.07
    å¾Ĺä¸Ĭ
    -0.07
    elts
    -0.07
    -so
    -0.07
    -prev
    -0.07
    áĥĶáĥĽ
    -0.07
    ç¼
    -0.07
    èĤ¯
    -0.07
    POSITIVE LOGITS
    ä¸į该
    0.08
    åĽłä¸ºå¥¹
    0.08
     pÅĻÃŃliÅ¡
    0.08
    æĽ´ä¸įè¦ģ
    0.08
    unless
    0.07
    èIJ¤
    0.07
    太好
    0.07
     Caldwell
    0.07
     melainkan
    0.07
     unless
    0.07
    Activations Density 0.324%

    No Known Activations