© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63077
    Prev
    Next
    INDEX
    Explanations

    simple, simplicity, keep it simple

    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
    饶
    -0.07
     somehow
    -0.07
    æĪĸåħ¶
    -0.07
    æĪĸèĢħæĺ¯
    -0.07
    åıĸèĢĮ代ä¹ĭ
    -0.06
    اÙĦب
    -0.06
    -or
    -0.06
    æħİ
    -0.06
    æĢİä¹ĪåĬŀåij¢
    -0.06
    cher
    -0.06
    POSITIVE LOGITS
    /simple
    0.10
     simplicity
    0.10
     Simp
    0.08
    没å¿ħè¦ģ
    0.08
    ãĤ·ãĥ³ãĥĹãĥ«
    0.08
    æľĢç®Ģåįķ
    0.08
    æľ¬æł¼
    0.08
    Simple
    0.08
    éĢļè¿ĩè¿Ļ次
    0.08
    æľĢç®ĢåįķçļĦ
    0.08
    Activations Density 0.009%

    No Known Activations