© 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. 17504
    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
    a
    -0.06
    éĻIJ
    -0.06
    aria
    -0.06
    r
    -0.06
    éĿ¢ç²ī
    -0.06
    èĩªåĬĽ
    -0.06
    ÃŃa
    -0.06
     vin
    -0.06
    åijĬ
    -0.06
    upt
    -0.06
    POSITIVE LOGITS
    biz
    0.09
    arker
    0.08
    unter
    0.08
    ockey
    0.08
    jach
    0.08
    åįģåĽĽç«ł
    0.08
    eed
    0.08
    stech
    0.08
    stry
    0.08
    зÑĢе
    0.08
    Activations Density 0.000%

    No Known Activations