© 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. 39207
    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
    樽
    -0.08
    æ²īæ²ī
    -0.07
    bies
    -0.07
    æĹłç§ģ
    -0.07
    otland
    -0.07
    åºĶæīĭ
    -0.07
    Commission
    -0.07
    ä¹ħèĢĮ
    -0.07
    "]).
    -0.07
    à¸ĺี
    -0.07
    POSITIVE LOGITS
    ABL
    0.07
    nf
    0.07
    redd
    0.07
    anam
    0.06
    amat
    0.06
    ç§ijåѦéĻ¢
    0.06
    è¦ģæ±Ĥåľ¨
    0.06
    à¸ŀรรà¸ĵ
    0.06
    (request
    0.06
     reinc
    0.06
    Activations Density 0.000%

    No Known Activations