© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    sibling, line, optional, photos

    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
    èĤĸ
    -0.07
    bat
    -0.07
    ¢
    -0.07
    edral
    -0.06
    brush
    -0.06
    гÑĢан
    -0.06
    å¯Ħ
    -0.06
    èĤĨ
    -0.06
    lesh
    -0.06
    ured
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    0.08
    istante
    0.07
    ãĤĤãĤĵ
    0.07
    uff
    0.07
    istes
    0.07
    æŁ¥çľĭæĽ´å¤ļä¿¡æģ¯
    0.06
    å°ıç¼ĸ为大家
    0.06
    å°¸
    0.06
    ÙĬØ«
    0.06
    Activations Density 0.008%

    No Known Activations