© 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. 29809
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    rtl
    -0.08
    ìĮį
    -0.08
    æĪŁ
    -0.08
    .xhtml
    -0.07
    æīģ
    -0.07
    对æķ´ä¸ª
    -0.07
    |"
    -0.07
    rt
    -0.07
    rtc
    -0.07
     Tutt
    -0.07
    POSITIVE LOGITS
    ATTER
    0.07
    åĨĻæĪIJ
    0.07
    atters
    0.07
    ÏĦÏģ
    0.07
    åĪĴåĪĨ为
    0.07
    åı¯ä¸º
    0.07
    åĪĻåı¯
    0.06
    人为
    0.06
     skr
    0.06
    å°±å°Ĩ
    0.06
    Activations Density 0.014%

    No Known Activations