© 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. 24633
    Prev
    Next
    INDEX
    Explanations

    examples for instance

    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
     either
    -0.08
    åIJĮçIJĨ
    -0.07
     Either
    -0.07
    å¦ĤæѤ
    -0.06
    either
    -0.06
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    -0.06
     presumably
    -0.06
    çĶ±åħ¶
    -0.06
     essentially
    -0.06
     thus
    -0.06
    POSITIVE LOGITS
    æĸĩ件æĪĸ
    0.11
    æĬķèµĦæĪĸ
    0.10
    æľįåĬ¡çŃī
    0.09
    å·¥ä½ľæĪĸ
    0.09
    å¤įåĪ¶æĪĸ
    0.09
    éĶĻ误æĪĸ
    0.09
    æŁIJ人
    0.08
    çĥ¨
    0.08
    æ´»åĬ¨çŃī
    0.08
    ãģĵãģ¨ãĤĦ
    0.08
    Activations Density 0.695%

    No Known Activations