© 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. 8405
    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
    Accept
    -0.07
    课
    -0.06
    åĪºæ¿Ģ
    -0.06
    ipline
    -0.06
    aly
    -0.06
     McCarthy
    -0.06
    éģĵ
    -0.06
    íĺ¼
    -0.06
    unal
    -0.06
    ä¸Ĭä¸ĭ
    -0.06
    POSITIVE LOGITS
    ä¹ĭæīĭ
    0.07
    è·¯éĢı
    0.07
    ences
    0.07
    çļĦè¿Ľè¡Į
    0.07
    èĢģå®ŀ
    0.07
    ekat
    0.07
    epass
    0.07
     mastur
    0.07
    ìŀĥ
    0.07
    ieve
    0.07
    Activations Density 0.000%

    No Known Activations