© 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. 34989
    Prev
    Next
    INDEX
    Explanations

    fall, fly, birds, grow

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    aum
    -0.07
    符
    -0.07
    人æķ°
    -0.07
    ait
    -0.07
    èĤĺ
    -0.06
    çķ¥
    -0.06
    åħĭåħ°
    -0.06
    严éĩįç¨ĭ度
    -0.06
    åĿIJéķĩ
    -0.06
     gradi
    -0.06
    POSITIVE LOGITS
    对人类
    0.09
    çļĦ使åij½
    0.09
    ä¼ļåijĺæľįåĬ¡
    0.08
    çĶŁåij½åij¨æľŁ
    0.08
    çĶ¨å¤Ħ
    0.08
    _tpl
    0.08
    é»ĺé»ĺæĹłéĹ»
    0.08
    èĩªæĪijçļĦ
    0.08
    ç»Ļ人们
    0.08
    为人们
    0.08
    Activations Density 0.025%

    No Known Activations