© 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. 10820
    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
    er
    -0.09
    ities
    -0.08
    istani
    -0.07
    ian
    -0.07
    a
    -0.07
    of
    -0.07
    ich
    -0.07
    rop
    -0.07
    ison
    -0.07
    ro
    -0.07
    POSITIVE LOGITS
    esModule
    0.09
    ï¸İ
    0.09
    ATRIX
    0.08
    æľ¬æł¼
    0.08
    请åijĬçŁ¥
    0.08
    伯ä¹IJ
    0.07
    ewood
    0.07
    teres
    0.07
    éĵģè¡Ģ
    0.07
     Gén
    0.07
    Activations Density 0.000%

    No Known Activations