© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    time estimation or process duration

    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
    ä¸Ģ段æŶéĹ´åIJİ
    -0.08
    éķ¿å¤§åIJİ
    -0.08
    ÙĤÙħ
    -0.08
    θÏħ
    -0.08
    ãģĹãģ°ãĤīãģı
    -0.07
    æŶéĹ´éķ¿äºĨ
    -0.07
     cedo
    -0.07
    æŶéĹ´ä¹ħäºĨ
    -0.07
    åĩłå¹´æĿ¥
    -0.07
    tsky
    -0.07
    POSITIVE LOGITS
    æīįå¼Ģå§ĭ
    0.10
    ä»įæľª
    0.08
    并å¼Ģå§ĭ
    0.08
     본격
    0.08
    ä¸ºå®ľ
    0.08
    ä»ĸå¼Ģå§ĭ
    0.08
    ãĤĪãģĨãĤĦãģı
    0.07
     begin
    0.07
    å°±å¼Ģå§ĭ
    0.07
    æĪijå¼Ģå§ĭ
    0.07
    Activations Density 0.345%

    No Known Activations