© 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. 3395
    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
    able
    -0.08
    enticated
    -0.07
    ern
    -0.07
    erder
    -0.06
    gegangen
    -0.06
    èĬĴ
    -0.06
    lege
    -0.06
    nn
    -0.06
    ofs
    -0.06
    osl
    -0.06
    POSITIVE LOGITS
    ATUS
    0.08
    isl
    0.08
    áĢ¸
    0.07
    çļ®çļĦ
    0.07
    ertas
    0.07
    注æĦıçļĦæĺ¯
    0.07
    ä¹ĭ书
    0.07
    Ø·ÙĬب
    0.07
    ystone
    0.07
    æĢĿæĺİ
    0.07
    Activations Density 0.000%

    No Known Activations