© 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. 25664
    Prev
    Next
    INDEX
    Explanations

    how is

    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
    sé
    -0.07
    abora
    -0.07
    并对åħ¶
    -0.07
    é½IJæĬĵ
    -0.07
    æĪijä¹Łæľī
    -0.07
    并æıIJåĩº
    -0.06
    æĺ¯ä¸Ģåıª
    -0.06
    导åĩºæķ°æį®
    -0.06
    å°Ĩåħ¶
    -0.06
    æľīä¸Ģåıª
    -0.06
    POSITIVE LOGITS
    æīį被
    0.10
    æĹ¥è¢«
    0.09
    ç§°ä½ľ
    0.09
     yapılır
    0.09
     нами
    0.09
    æ¯Ķä½ľ
    0.08
    åı¯èĥ½è¢«
    0.08
    æķ°æį®è¿Ľè¡Į
    0.08
    éĹ®é¢ĺè¿Ľè¡Į
    0.08
    empt
    0.08
    Activations Density 0.122%

    No Known Activations