© 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. 65035
    Prev
    Next
    INDEX
    Explanations

    rates of change

    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
    常è§ĦçļĦ
    -0.07
     qualific
    -0.07
    ä¸½å¨ľ
    -0.07
    大éĻ¢
    -0.07
     Peker
    -0.07
    اÙĨØ´
    -0.07
    延伸
    -0.07
    åĿļ
    -0.07
    é¡
    -0.07
     préc
    -0.07
    POSITIVE LOGITS
     slowly
    0.12
    æħ¢æħ¢
    0.11
    æľĢå¿«
    0.11
     fastest
    0.10
     gradual
    0.10
     quickest
    0.10
    æĽ´å¿«
    0.10
     gradually
    0.10
    ç¼ĵæħ¢
    0.10
    å¾Īæħ¢
    0.10
    Activations Density 0.047%

    No Known Activations