© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    . purchased this

    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
    对ä¸Ĭè¿°
    -0.11
    è¿Ŀåıįä¸Ĭè¿°
    -0.10
    ajara
    -0.09
    å¼ĦèĻļ
    -0.08
    ä½ľåĪĻ
    -0.08
    æĥĬå¿ĥåĬ¨
    -0.08
    æľīæĽ´å¤ļçļĦ
    -0.08
    orca
    -0.08
    ä¹ŁæŃ£æĺ¯
    -0.08
    \/\/
    -0.08
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.07
    çĴŀ
    0.07
    0.06
    2
    0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.06
    ãģ¾ãģļ
    0.06
    0.06
    [
    0.05
    UTH
    0.05
    č↵
    0.05
    Activations Density 0.085%

    No Known Activations