© 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. 25304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    秫
    -0.08
     youngest
    -0.07
    ä½łæĢİä¹Ī
    -0.07
    емов
    -0.07
    atty
    -0.07
     cheapest
    -0.07
    igen
    -0.07
    erner
    -0.06
     simplest
    -0.06
    ciel
    -0.06
    POSITIVE LOGITS
    å±±ä¸ĭ
    0.07
    ursa
    0.07
    ä¹IJ天
    0.07
    ooth
    0.07
    æĶ¯æĮģä¸ĭ
    0.07
    cec
    0.07
    akwa
    0.07
    åħ¨åľº
    0.06
    åIJīæĸ¯
    0.06
    Äģj
    0.06
    Activations Density 0.000%

    No Known Activations