© 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. 25379
    Prev
    Next
    INDEX
    Explanations

    equations with numbers

    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
    à¹ģหละ
    -0.07
     appunto
    -0.07
    ëĤĺë§Ī
    -0.07
    å®ķ
    -0.07
     unnamed
    -0.07
    comed
    -0.06
    人对
    -0.06
    éŨåħ³
    -0.06
     Shelter
    -0.06
    äººæł¼
    -0.06
    POSITIVE LOGITS
    æıIJé«ĺåѦçĶŁ
    0.08
    ite
    0.07
    uve
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    ÃŃc
    0.07
    xis
    0.07
    нÑĸ
    0.07
    ÙĦÙĪ
    0.07
    ï
    0.07
    но
    0.07
    Activations Density 0.003%

    No Known Activations