© 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. 23319
    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
    ç½ķ
    -0.09
    ught
    -0.09
    gaz
    -0.08
     ÄijÃł
    -0.08
    躲
    -0.07
    gmt
    -0.07
    iest
    -0.07
    лови
    -0.07
    tings
    -0.07
    cante
    -0.07
    POSITIVE LOGITS
    i
    0.07
    uolo
    0.07
    å½ĵæŶçļĦ
    0.06
    ng
    0.06
    uffed
    0.06
    ä¸īçľģ
    0.06
    æĽĻ
    0.06
    ocy
    0.06
    游è¡Į
    0.06
    clared
    0.06
    Activations Density 0.000%

    No Known Activations