© 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. 13103
    Prev
    Next
    INDEX
    Explanations

    timestamps and timezones

    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
    ~=
    -0.08
    çĴĭ
    -0.08
    ¬ģ
    -0.08
     ìĮ¤
    -0.08
    æijĩ头
    -0.08
    ç¯ĩä¸Ģ
    -0.08
    isci
    -0.07
    iesz
    -0.07
     ë©ķ
    -0.07
    jdbc
    -0.07
    POSITIVE LOGITS
    å¾ĭ
    0.07
     labelText
    0.07
    .every
    0.07
    fall
    0.06
    æ¯ıä¸Ģ天
    0.06
    æ³ķå®ļ
    0.06
    ä¼ı
    0.06
    ulut
    0.06
    åħīåĴĮ
    0.06
    åĬłåĭĴ
    0.06
    Activations Density 0.047%

    No Known Activations