© 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. 24724
    Prev
    Next
    INDEX
    Explanations

    context for lists

    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
    åŀ£
    -0.08
    .microsoft
    -0.07
    .Maybe
    -0.07
    anger
    -0.07
    etus
    -0.07
     wyn
    -0.06
    itian
    -0.06
     nad
    -0.06
    èIJ¤çģ«
    -0.06
    ä¼ĺç§Ģåħ±äº§åħļåijĺ
    -0.06
    POSITIVE LOGITS
     meanwhile
    0.09
    éħįç½®æĸ¹éĿ¢
    0.08
     оÑģÑĤалÑĮнÑĭÑħ
    0.08
    åĪĻéľĢè¦ģ
    0.08
    anton
    0.08
    æĸ¹éĿ¢ä¹Ł
    0.08
    çĦ¶åIJİæĺ¯
    0.08
    èĢĮ对äºİ
    0.08
    æİ¥ä¸ĭæĿ¥
    0.08
     regard
    0.07
    Activations Density 0.037%

    No Known Activations