© 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. 63204
    Prev
    Next
    INDEX
    Explanations

    finite fields

    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
    æīĢæľī人
    -0.07
    isko
    -0.07
    Ïģά
    -0.07
    ologe
    -0.07
    çľģ缴
    -0.07
    auta
    -0.07
     макÑģимÑĥм
    -0.07
    лоÑĤо
    -0.06
    chants
    -0.06
    δοÏĤ
    -0.06
    POSITIVE LOGITS
    ess
    0.07
    个好
    0.07
    ähler
    0.07
    (resp
    0.06
    øk
    0.06
    imate
    0.06
    ึà¸ģ
    0.06
    å¹¢
    0.06
    ên
    0.06
    ness
    0.06
    Activations Density 0.011%

    No Known Activations