© 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. 65200
    Prev
    Next
    INDEX
    Explanations

    fields required

    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
    aldi
    -0.08
    ackt
    -0.07
    athi
    -0.07
    hto
    -0.07
    æħ·
    -0.07
    Åijr
    -0.07
    ibri
    -0.07
    chung
    -0.07
     Hath
    -0.07
     Ñģоле
    -0.07
    POSITIVE LOGITS
    -vars
    0.07
    IMPORTANT
    0.07
    omo
    0.07
    åĴĮéĥ¨åĪĨ
    0.07
    _HIDDEN
    0.07
    æ¯ıåŃ¦æľŁ
    0.07
    书è¯Ħ
    0.07
    äºĨåĽŀæĿ¥
    0.07
    fld
    0.06
    ä¹ĭäºĮ
    0.06
    Activations Density 0.001%

    No Known Activations