© 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. 13704
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    åħ¶ä»ĸåªĴä½ĵ
    -0.08
    为ä»Ģä¹Ī说
    -0.08
    æĥ³çľĭ
    -0.08
    essus
    -0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.07
    æĽ´æľīåĪ©äºİ
    -0.07
    oser
    -0.07
    çŀŃ
    -0.07
    iev
    -0.07
     пÑĢоÑĩие
    -0.07
    POSITIVE LOGITS
     entweder
    0.10
    Either
    0.09
     либо
    0.09
     either
    0.09
    åı¯éĩĩçĶ¨
    0.09
     Either
    0.09
    à¸Ĺำà¹Ħà¸Ķà¹ī
    0.09
    åı¯ä½¿çĶ¨
    0.09
    åı¯ä»¥éĩĩçĶ¨
    0.08
    either
    0.08
    Activations Density 0.295%

    No Known Activations