© 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. 25716
    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
    ible
    -0.09
    ey
    -0.07
    æľī好
    -0.07
    æĢ§å¼º
    -0.06
    cape
    -0.06
    ory
    -0.06
    arg
    -0.06
    iamo
    -0.06
    ä¹ĭ梦
    -0.06
    ivity
    -0.06
    POSITIVE LOGITS
    åIJīæĸ¯
    0.09
     (;;
    0.08
    letes
    0.08
    ered
    0.07
    =label
    0.07
    emuk
    0.07
    elte
    0.07
    asen
    0.07
    alet
    0.07
    assem
    0.07
    Activations Density 0.000%

    No Known Activations