© 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. 47203
    Prev
    Next
    INDEX
    Explanations

    stay + condition

    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
    .nz
    -0.09
    jenigen
    -0.09
    ÙĨÙĩ
    -0.09
     ë¶ĢíĦ°
    -0.09
    ä¸įèĥľ
    -0.09
    ussen
    -0.08
    sweise
    -0.08
     menyar
    -0.08
    ãģĦãģĨ
    -0.08
    schen
    -0.08
    POSITIVE LOGITS
    alive
    0.08
    åĴĮæĶ¹åĸĦ
    0.07
    باع
    0.07
    /change
    0.07
    ting
    0.07
    å¾Ĺä½ı
    0.07
    åĴĮæıIJåįĩ
    0.07
    ably
    0.07
    stay
    0.07
    åİŁåľ°
    0.07
    Activations Density 0.027%

    No Known Activations