© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions

    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
    åī¯ä¹¦è®°
    -0.08
    rie
    -0.08
    åħ³äºİå¼Ģå±ķ
    -0.07
    Occurred
    -0.07
    unn
    -0.07
    é¤ĺ
    -0.07
    ä½Ļè£ķ
    -0.07
    cntl
    -0.06
    aji
    -0.06
    æĺ¯æĮĩ
    -0.06
    POSITIVE LOGITS
    andos
    0.07
    ificare
    0.07
    ÈĻi
    0.07
    æĸĩåįļ
    0.07
    _each
    0.07
    åı¯ä»¥çIJĨ解
    0.07
     inherently
    0.07
    ibble
    0.07
    æĪIJ羣
    0.07
     compon
    0.07
    Activations Density 0.013%

    No Known Activations