© 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. 9857
    Prev
    Next
    INDEX
    Explanations

    eth file

    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
    íħĮíģ¬
    -0.08
    -syntax
    -0.07
    bal
    -0.07
    -X
    -0.07
    :X
    -0.07
     Doors
    -0.07
    chu
    -0.06
    onyme
    -0.06
    atori
    -0.06
    ót
    -0.06
    POSITIVE LOGITS
    æĺ¥åįİ
    0.08
    åħ¬åı¸æݨèįIJ
    0.07
    undle
    0.07
    åħ¬åı¸æ³¨åĨĮ
    0.07
     Wyatt
    0.07
    çIJµ
    0.06
    没è¿ĩ
    0.06
     Galler
    0.06
    {}_
    0.06
    没å¤ļä¹ħ
    0.06
    Activations Density 0.056%

    No Known Activations