© 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. 64643
    Prev
    Next
    INDEX
    Explanations

    greetings

    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
    å¾Ĺ以
    -0.07
    è°
    -0.06
    )").
    -0.06
    ç¬ijçĿĢ说éģĵ
    -0.06
    çªľ
    -0.06
    éĺ»
    -0.06
    ä¸ĩäºĭå¦ĤæĦı
    -0.06
    èĵ¬åĭĥåıijå±ķ
    -0.06
    æĮ¯
    -0.06
    å¾ĹçļĦ
    -0.06
    POSITIVE LOGITS
    æİ¥ä¸ĭ
    0.09
    éĿ¢æĹłè¡¨æĥħ
    0.08
    åĨ·æ·¡
    0.08
     trocken
    0.08
    ilent
    0.08
    ä¸įæĥĬ
    0.08
    ä¸įèĭŁ
    0.08
    åĨ·éĿĻ
    0.08
    IFS
    0.08
     concise
    0.08
    Activations Density 0.003%

    No Known Activations