© 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. 37659
    Prev
    Next
    INDEX
    Explanations

    `@author` colon

    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
    onet
    -0.08
    ä¸įæĬĺä¸įæī£
    -0.07
    aise
    -0.07
    ãģŁãģ¨
    -0.07
     frozen
    -0.07
    ä¸Ģèĩ³
    -0.07
    _OVERRIDE
    -0.07
    à¥ģरà¥ģ
    -0.07
    aises
    -0.06
    ä¸įèĭŁ
    -0.06
    POSITIVE LOGITS
    æŁIJç§į
    0.10
    åı¯ä»¥èĢĥèĻij
    0.10
     something
    0.10
     useful
    0.10
    æĪĸ许
    0.09
    åı¯ä»¥çĶ¨æĿ¥
    0.09
    åı¯ä»¥åĪ©çĶ¨
    0.09
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.09
    çĶ¨å¤Ħ
    0.09
    æŁIJ種
    0.09
    Activations Density 0.008%

    No Known Activations