© 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. 18765
    Prev
    Next
    INDEX
    Explanations

    student-led initiative

    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
    就象
    -0.10
    æĥŁä¸Ģ
    -0.10
     idéia
    -0.09
    好象
    -0.09
     parms
    -0.09
    å¹´éĿĴ
    -0.09
    .htm
    -0.09
    ãģ§ãģĻãģĭãĤī
    -0.08
    èĩªå·²
    -0.08
    	StringBuffer
    -0.08
    POSITIVE LOGITS
    缸è¾ĥäºİ
    0.13
    -esque
    0.13
     entirety
    0.11
     kì
    0.10
    æĦĪåıij
    0.10
    缸æ¯Ķäºİ
    0.10
    åıĪæĪĸèĢħ
    0.10
    ä¸Ģä¼Ĺ
    0.10
    âĻ¡
    0.10
    ⾨
    0.09
    Activations Density 2.288%

    No Known Activations