© 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. 17399
    Prev
    Next
    INDEX
    Explanations

    using a method

    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
    人æĪĸ
    -0.10
    éĶĻ误æĪĸ
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    æŁIJç§į
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
     somehow
    -0.07
    åıij表æĪĸ
    -0.07
     somewhere
    -0.07
    çŃīåħ¶ä»ĸ
    -0.07
    ä¸Ģèµ·åIJĥ
    -0.07
    POSITIVE LOGITS
    为载ä½ĵ
    0.07
    æ¯Ĥ
    0.07
    åĽ½å®¶ä¸Ģ级
    0.07
    åĻ¨åĴĮ
    0.07
    ä¸ĩä½Ļ
    0.07
    çĤ¹å¤ļ
    0.06
    viso
    0.06
    jemy
    0.06
     mic
    0.06
    éļ¶å±ŀäºİ
    0.06
    Activations Density 2.200%

    No Known Activations