© 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. 33961
    Prev
    Next
    INDEX
    Explanations

    formula comparison rather than

    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
    راد
    -0.07
    æĮīè¦ģæ±Ĥ
    -0.07
     pá
    -0.06
    aises
    -0.06
    iedz
    -0.06
     pese
    -0.06
     Desired
    -0.06
    粧
    -0.06
    OTTO
    -0.06
     unsuccessfully
    -0.06
    POSITIVE LOGITS
    æĺ¯å¯¹çļĦ
    0.08
    åħ¬å¼ı
    0.08
    åĽłä¸ºæĺ¯
    0.07
    ä¸įåĩı
    0.07
    å½·
    0.07
    åĽłä¸ºä½ł
    0.07
    没éĶĻ
    0.07
    å¦Ĥæŀľæĺ¯
    0.07
    åıĸèĩª
    0.07
     subsidi
    0.07
    Activations Density 0.005%

    No Known Activations