© 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. 28859
    Prev
    Next
    INDEX
    Explanations

    mathematical notation for all

    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
     simplest
    -0.07
    ä¸Ģ天天
    -0.07
    asion
    -0.06
     alternate
    -0.06
    ä¸ĢèĪ¬æĺ¯
    -0.06
     Alternate
    -0.06
    owi
    -0.06
    зиÑĢов
    -0.06
     succeeded
    -0.06
    Alternate
    -0.06
    POSITIVE LOGITS
    ä¸įèĩ³äºİ
    0.10
    ä¸Ģ个æľĪåĨħ
    0.08
    ordu
    0.08
    两åij¨åĨħ
    0.08
    è·Ŀ
    0.08
    öl
    0.08
     entro
    0.08
    lej
    0.07
    _frontend
    0.07
     unpl
    0.07
    Activations Density 0.009%

    No Known Activations