© 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. 4279
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

    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
    inden
    -0.07
    enge
    -0.07
    åĨ
    -0.07
    hist
    -0.07
     dijer
    -0.07
    ä¹ŁæĹłæ³ķ
    -0.07
    ä¹Łæ²Ĵ
    -0.07
    ä¸įåħ¥
    -0.07
    Stuff
    -0.07
    occa
    -0.07
    POSITIVE LOGITS
    akwa
    0.08
    å¤ļä¸ĢçĤ¹
    0.07
     Ø£Ùħ
    0.07
    个人æĪĸ
    0.07
    å¤ļä¸ĢäºĽ
    0.07
    æħ·
    0.07
    seo
    0.06
     ÙĪÙĩÙĦ
    0.06
    озна
    0.06
    à¸Īริà¸ĩ
    0.06
    Activations Density 0.002%

    No Known Activations