© 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. 58866
    Prev
    Next
    INDEX
    Explanations

    written and directed

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸåħ¶ä»ĸ
    -0.11
    æĪĸåħ¶å®ĥ
    -0.10
    æĪĸèĢħåħ¶ä»ĸ
    -0.10
    æĪĸ对
    -0.08
    otta
    -0.08
    ertools
    -0.08
    æĪĸä¸İ
    -0.07
    æĪĸéĿŀ
    -0.07
    abei
    -0.07
    æĪĸ个人
    -0.07
    POSITIVE LOGITS
    åĴĮæī§è¡Į
    0.17
    并å®ĮæĪIJ
    0.16
    à¹ģละà¸ģาร
    0.14
    并ç»Ħç»ĩ
    0.14
    åĴĮè¡ĮåĬ¨
    0.13
    并å¼Ģå§ĭ
    0.13
    å¹¶è¿Ľè¡Į
    0.13
    并使çĶ¨
    0.13
    并éĩĩåıĸ
    0.12
    并æĮīçħ§
    0.12
    Activations Density 0.801%

    No Known Activations