© 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. 32392
    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
    lay
    -0.08
    ov
    -0.07
    atch
    -0.07
    第ä¸Ģæī¹
    -0.07
    éħįåIJĪ
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
     sucker
    -0.07
    gets
    -0.07
    zn
    -0.07
    สิà¸Ļ
    -0.06
    POSITIVE LOGITS
    gnu
    0.07
    为ä½ķ
    0.07
    abox
    0.07
    ä¸ĢçĽĺ
    0.07
    çļĦä¸ĵæłı
    0.07
    ParameterValue
    0.07
    åĿŀ
    0.07
    -divider
    0.07
    kode
    0.07
    çĤºä½ķ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.