© 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. 13332
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    çļĦäºĨ
    -0.09
    çļĦæŶåĢĻäºĨ
    -0.09
    çļĦäºĭæĥħäºĨ
    -0.08
    æľīæīĢä¸ĭéĻį
    -0.08
    ä¹ŁæľīäºĽ
    -0.08
    ÃģP
    -0.08
    çļĦäºĭäºĨ
    -0.07
    obet
    -0.07
    çļĦéĤ£æł·
    -0.07
    èĢĮéĻį
    -0.07
    POSITIVE LOGITS
     voilÃł
    0.13
     itulah
    0.11
    æĢ§æĺ¯
    0.10
     inilah
    0.10
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.10
    æĺ¯å¾Īå¤ļ
    0.10
    æĺ¯æľ¬
    0.09
    è¿Ļæĺ¯
    0.09
    igh
    0.09
    æĺ¯æĪijåĽ½
    0.09
    Activations Density 0.454%

    No Known Activations