© 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. 56205
    Prev
    Next
    INDEX
    Explanations

    in preparation, thinking ahead

    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
    akis
    -0.10
    ost
    -0.07
    å¿ħé¡»åĿļæĮģ
    -0.06
    åĪĨç«Ļ
    -0.06
     conform
    -0.06
    为æĤ¨ä»ĭç»į
    -0.06
    æĹ¥å¸¸çĶŁæ´»ä¸Ń
    -0.06
    ISIBLE
    -0.06
    zis
    -0.06
    parse
    -0.06
    POSITIVE LOGITS
    åĩĨå¤ĩ好
    0.17
     prepared
    0.16
     заÑĢанее
    0.16
    prepared
    0.15
    åĩĨå¤ĩçļĦ
    0.15
    æıIJåīį
    0.15
    åĩĨå¤ĩ好çļĦ
    0.15
    åĩĨå¤ĩ
    0.15
    å¿ĥçIJĨåĩĨå¤ĩ
    0.15
    åĩĨå¤ĩäºĨ
    0.15
    Activations Density 0.271%

    No Known Activations