© 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. 40126
    Prev
    Next
    INDEX
    Explanations

    associated or lead to

    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
    à¹Ģà¸Ĺศ
    -0.08
    æ·±åıĹ广大
    -0.08
    etzen
    -0.07
    åı¯èĥ½ä¼ļ对
    -0.07
    azza
    -0.07
    äºĮéĥİ
    -0.07
    ãģıãĤĵ
    -0.07
    kuš
    -0.07
     Giunta
    -0.07
    ä¸įèĥ½è®©
    -0.07
    POSITIVE LOGITS
     seco
    0.07
    åĽłåħ¶
    0.07
    åĽłä¸ºåħ¶
    0.07
     ÑĥÑģпеÑħа
    0.06
    æľªå¿ħ
    0.06
    nda
    0.06
    оÑĢга
    0.06
    æ¼Ķèīº
    0.06
    vida
    0.06
    çļĦç»ĵåIJĪ
    0.06
    Activations Density 0.148%

    No Known Activations