© 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. 56183
    Prev
    Next
    INDEX
    Explanations

    mathematical notation delimiters

    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
    à¸ĩ
    -0.08
    ¢
    -0.07
    æ¯ıæĹ¥ä¸Ģç»ĥ
    -0.07
    çĸ±
    -0.07
    éĹ®é¢ĺæŶ
    -0.07
    µ¬
    -0.07
    pired
    -0.07
    kast
    -0.07
    为ä»Ģä¹Īä¸į
    -0.07
    æĸ°å¤©åľ°
    -0.06
    POSITIVE LOGITS
    areth
    0.07
    ä¸ºæľŁ
    0.07
     ((__
    0.07
     lần
    0.07
     represents
    0.07
    æĺ¯ä¸ĸçķĮ
    0.07
    ëŀĢ
    0.07
     Aviv
    0.07
     denotes
    0.07
    æĺ¯åħ¨çIJĥ
    0.07
    Activations Density 0.009%

    No Known Activations