© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34739
    Prev
    Next
    INDEX
    Explanations

    numerical digits or dates in formal or technical text.

    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
    äºĮèĢħ
    -0.08
    âĢ¦
    -0.07
    åĽłèĢĮ
    -0.07
    ä¹ĭç±»
    -0.07
    èĻ½
    -0.07
    âĢij
    -0.07
    åĴ±
    -0.07
    æĺ¥åįİ
    -0.07
    头
    -0.07
    å°¤åħ¶
    -0.07
    POSITIVE LOGITS
    éĻĦä¸Ĭä¸Ģ
    0.07
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    0.07
    åī©ä¸ĭçļĦ
    0.07
    æĪijæĿ¥è¯´ä¸¤åı¥
    0.07
    %",
    0.07
    没æľīæī¾åĪ°
    0.07
    _",
    0.07
    istring
    0.07
    æīįèĥ½æĽ´å¥½åľ°
    0.07
    没æľīåĩºçİ°
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.