© 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. 34458
    Prev
    Next
    INDEX
    Explanations

    automated contexts

    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
    èIJ¥éĶĢçŃĸçķ¥
    -0.07
    çģµæ´»è¿IJçĶ¨
    -0.07
    .Platform
    -0.07
    ña
    -0.07
    æķĻèĤ²æĶ¹éĿ©
    -0.07
    æŃ£å¸¸ä½¿çĶ¨
    -0.06
    ÅĤoÅĽci
    -0.06
    æķħæĦı
    -0.06
    wise
    -0.06
    éĢĨ
    -0.06
    POSITIVE LOGITS
    èĩªåĬ¨åĮĸ
    0.19
     automated
    0.18
     automate
    0.17
    èĩªåĬ¨
    0.16
     automation
    0.16
     autom
    0.15
     automat
    0.15
     automatis
    0.15
     Automated
    0.15
    èĩªåĭķåĮĸ
    0.15
    Activations Density 0.218%

    No Known Activations