© 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. 31036
    Prev
    Next
    INDEX
    Explanations

    empty values or missing data

    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
    Ĥ¹
    -0.09
    缴åij¼
    -0.08
    临åħ¶
    -0.07
    icap
    -0.07
    æľªç»ı
    -0.07
    .capture
    -0.07
    teles
    -0.07
    nyata
    -0.07
    èĺĭ
    -0.07
    ÐłÐŀÐĴ
    -0.07
    POSITIVE LOGITS
    _intent
    0.07
    æĢ§æĪĸ
    0.07
    ä¸Ģ空
    0.07
     intents
    0.07
    æģ¯
    0.07
    à¹Ħà¸Ł
    0.06
    ä¸Ń度
    0.06
    azor
    0.06
     Blank
    0.06
    度é«ĺ
    0.06
    Activations Density 0.011%

    No Known Activations