© 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. 8472
    Prev
    Next
    INDEX
    Explanations

    I have no idea

    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
    éĩijæĸ¯
    -0.08
    uhn
    -0.07
    HN
    -0.07
    dds
    -0.07
     vir
    -0.07
     ÙĪÙħص
    -0.07
    dda
    -0.07
    ç¼
    -0.06
     stip
    -0.06
     cor
    -0.06
    POSITIVE LOGITS
    ç®Ĺä¸įä¸Ĭ
    0.09
    ä¸įç®Ĺ
    0.08
    åIJįåī¯åħ¶å®ŀ
    0.08
     qualify
    0.08
    ç®Ĺå¾Ĺä¸Ĭ
    0.08
     qualifies
    0.08
    æľ¬è´¨ä¸Ĭ
    0.08
     оÑĤнеÑģÑĤи
    0.08
     arguably
    0.08
    ç®Ĺæĺ¯
    0.07
    Activations Density 0.052%

    No Known Activations