© 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. 63623
    Prev
    Next
    INDEX
    Explanations

    from followed by a word

    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
    à¹ģมà¹īà¹ģà¸ķà¹Ī
    -0.06
    ÅĽc
    -0.06
    æĦıä¹īä¸ĬçļĦ
    -0.06
    RequestMethod
    -0.06
    TTY
    -0.06
    igin
    -0.06
    æīĢ称
    -0.06
    åľ¨è¿Ļ
    -0.06
    ä½ľä¸ºä¸ĢåIJį
    -0.06
    çĶļèĩ³æĺ¯
    -0.06
    POSITIVE LOGITS
    åı¯çŁ¥
    0.10
    èĢĮçŁ¥
    0.09
    ä¸ŃæıIJåıĸ
    0.09
    åIJİåı¯
    0.09
    æĪijä»¬çŁ¥éģĵ
    0.09
    é¢ĺæĦı
    0.09
     извеÑģÑĤно
    0.08
    åı¯å¾Ĺ
    0.08
    å¾Ĺåħ¶
    0.08
    æĹ¥èµ·
    0.08
    Activations Density 0.014%

    No Known Activations