© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    syntactic patterns around code and text

    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
    .annotations
    -0.09
    æĽ´å¤ļ精彩
    -0.09
    åıįè¶ħ
    -0.08
     theirs
    -0.08
    æł¼å¤ĸ
    -0.08
    æľĢå¾Įãģ¾ãģ§
    -0.08
    remen
    -0.08
     vinh
    -0.08
    è¿ĶåĽŀåĪĹ表
    -0.08
    chg
    -0.08
    POSITIVE LOGITS
    .But
    0.10
    æĮīçIJĨ
    0.10
     supposedly
    0.10
     ÑıкобÑĭ
    0.10
    ä¼¼ä¹İ
    0.10
     supposed
    0.10
    ä¼¼ä¹İæĺ¯
    0.10
     ostensibly
    0.09
    ä½Ĩè¿Ļ
    0.09
    確ãģĭãģ«
    0.09
    Activations Density 1.102%

    No Known Activations