© 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. 46124
    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
    ught
    -0.07
    转载èĩ³
    -0.07
    "https
    -0.07
    rides
    -0.07
    oleh
    -0.06
    à¹Ģà¸Ī
    -0.06
    uket
    -0.06
     "</
    -0.06
     )"
    -0.06
    第åįģåħ«
    -0.06
    POSITIVE LOGITS
    æѦåĬŁ
    0.08
    å¥ĩå¦Ļ
    0.07
    è¡Ģ
    0.07
    æĪĸå¤ļ个
    0.07
    åľ¨æĹł
    0.07
    åĩºä¸Ģéģĵ
    0.07
    æ¯ĴçĹĩ
    0.07
     ÑģÑĥм
    0.06
    æĪĸå¤ļ
    0.06
    до
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.