© 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. 19021
    Prev
    Next
    INDEX
    Explanations

    section or part identifier

    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
    æľ¬æĸĩ为åįļ主
    -0.08
     Morm
    -0.08
    inton
    -0.08
    enner
    -0.08
    å½ĵä¹ĭ
    -0.08
    йки
    -0.08
    æĹłè¸ª
    -0.08
    ä¼ĺç§Ģåħ±äº§åħļåijĺ
    -0.08
    ÙĥÙĪÙħ
    -0.07
    æ¸ħæ¸ħæ¥ļæ¥ļ
    -0.07
    POSITIVE LOGITS
    vere
    0.06
    çİ«
    0.06
    anoia
    0.06
    çłĶ究表æĺİ
    0.06
    maal
    0.06
    ĶĦ
    0.06
    UFF
    0.06
    èĬ±æŀľ
    0.06
     Karn
    0.05
     Roos
    0.05
    Activations Density 0.019%

    No Known Activations