© 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. 62688
    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
    ogue
    -0.07
    baran
    -0.07
    æĮģåį¡
    -0.06
    ä¸ĢæĹı
    -0.06
    æŀķ
    -0.06
     crossorigin
    -0.06
     opt
    -0.06
    kin
    -0.06
    p
    -0.06
    برد
    -0.06
    POSITIVE LOGITS
    akter
    0.09
    usus
    0.08
    errat
    0.08
    NotAllowed
    0.08
    лÑıн
    0.08
    zsche
    0.08
    ackt
    0.08
    æĹłåĩł
    0.07
    utih
    0.07
    ÑĢово
    0.07
    Activations Density 0.000%

    No Known Activations