© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2479
    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
    rake
    -0.07
    erts
    -0.07
    yka
    -0.07
    oule
    -0.06
    æĹ¢åı¯
    -0.06
     обо
    -0.06
    ylon
    -0.06
    ä¿ĺ
    -0.06
    erner
    -0.06
    æĹłè®ºä»İ
    -0.06
    POSITIVE LOGITS
    éļĶ天
    0.09
    ptom
    0.08
    éłĺ
    0.07
    éĻ¤æģ¶
    0.07
    عÙĩ
    0.07
    geries
    0.07
    alow
    0.07
    éĻ¤å¤ĸ
    0.07
    chn
    0.07
    ãĥıãĤ¤
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.