© 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. 57913
    Prev
    Next
    INDEX
    Explanations

    text content from code files or technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     crazy
    -0.09
    ارÛĮ
    -0.08
     basically
    -0.08
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.08
    åŁºæľ¬ä¸Ĭ
    -0.08
    åĴĮåIJĦç§į
    -0.08
    è¿Ļ个ä¸ĸçķĮä¸Ĭ
    -0.07
    åľ¨ä¸įåIJĮçļĦ
    -0.07
    åºĶ该ä¼ļ
    -0.07
     crappy
    -0.07
    POSITIVE LOGITS
    ä»įæľª
    0.08
    \_
    0.08
    已形æĪIJ
    0.07
    ä»ħä½ľ
    0.07
    并æĹł
    0.07
    çİĩè¾¾
    0.07
    —not
    0.07
    大åı¯
    0.07
    èĻ½
    0.07
    è¾ħ以
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.