© 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. 11538
    Prev
    Next
    INDEX
    Explanations

    That's right

    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
    .constructor
    -0.09
    æĹĹä¸ĭ
    -0.08
    ärzt
    -0.08
    usch
    -0.08
    ä¸ĭè¿°
    -0.07
    åŁºäºİ
    -0.07
     dici
    -0.07
    orge
    -0.07
    ocket
    -0.07
     Brands
    -0.07
    POSITIVE LOGITS
     **.**
    0.06
    ä¸İåĪĨæŀIJ
    0.06
    anned
    0.06
     corde
    0.06
    èĽ
    0.06
     pant
    0.06
    çĨĻ
    0.06
    çĸ¥
    0.06
    èĤ¯å®ļçļĦ
    0.06
    ä¸įå°ıå¿ĥ
    0.06
    Activations Density 0.002%

    No Known Activations