© 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. 17842
    Prev
    Next
    INDEX
    Explanations

    truth be told, be honest, face it

    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
    认è¯ĨäºĨ
    -0.08
    æĹłéĹ»
    -0.08
    使çĶ¨ä¸Ń
    -0.08
    大好
    -0.08
    annes
    -0.08
    çŁ¥éģĵèĩªå·±çļĦ
    -0.08
    ãĥĥãĤŃ
    -0.08
    Ŀ
    -0.07
    纶
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
    æĿ¥è¯´
    0.09
    edly
    0.08
    èĢĮè¨Ģ
    0.08
    è¨ĢãģĪãģ°
    0.08
    åľ°è¯´
    0.07
    èĢĮè¨Ģä¹ĭ
    0.07
    è«
    0.07
    ingly
    0.07
    说ä¸į
    0.07
    ä¾Ĩ說
    0.06
    Activations Density 0.431%

    No Known Activations