© 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. 16972
    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
    fact
    -0.09
    ÑıÑĤÑĮÑģÑı
    -0.07
    ັàºĻ
    -0.07
    ä»Ĭå¤ľ
    -0.07
     Anno
    -0.07
    stell
    -0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
     lithium
    -0.07
     facto
    -0.07
     Fact
    -0.07
    POSITIVE LOGITS
    访
    0.08
    ording
    0.07
    è¨ĺ
    0.07
    訪
    0.06
    uggy
    0.06
    ilere
    0.06
    ض
    0.06
    emas
    0.06
    .Named
    0.06
    plex
    0.06
    Activations Density 0.000%

    No Known Activations