© 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. 51629
    Prev
    Next
    INDEX
    Explanations

    api and related endpoints

    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
    éĤªéŃĶ
    -0.08
    éħįç½®æĸ¹éĿ¢
    -0.08
    RTL
    -0.08
    ÃŃn
    -0.08
    ogne
    -0.08
    olim
    -0.08
     ìłĦìŀ¬
    -0.08
    ]()
    -0.07
    StartupScript
    -0.07
    OOT
    -0.07
    POSITIVE LOGITS
     API
    0.11
     APIs
    0.10
    _api
    0.10
    -api
    0.09
     api
    0.09
    Api
    0.09
    api
    0.09
     Api
    0.08
    API
    0.08
    	api
    0.07
    Activations Density 0.277%

    No Known Activations