© 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. 26674
    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
    asso
    -0.09
    amore
    -0.07
    alai
    -0.07
    _cn
    -0.07
    ueil
    -0.07
    ativ
    -0.07
    jemu
    -0.07
    apa
    -0.07
    atz
    -0.07
    ä¸įæį¢
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.07
    èĢĮåIJĮ
    0.07
    ìļ±
    0.06
    estig
    0.06
    Uploaded
    0.06
    emor
    0.06
    -padding
    0.06
    åĭĴæĸ¯
    0.06
    åĩºåı£çļĦ
    0.06
    ẫn
    0.06
    Activations Density 0.000%

    No Known Activations