© 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. 56788
    Prev
    Next
    INDEX
    Explanations

    anisotropic

    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
    åĴĮçłĶ究
    -0.08
    تاÙĨ
    -0.07
    INGS
    -0.07
    تÙĥ
    -0.07
    åĴĮç»ıæµİ
    -0.06
    ×ķת
    -0.06
    à¹Ģà¸Ħียà¸ĩ
    -0.06
    常说çļĦ
    -0.06
    ese
    -0.06
    ////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
    æĢ§çļĦ
    0.09
    uka
    0.08
     xạ
    0.08
    ÑĥÑģа
    0.08
    ç¨ĭ度
    0.08
    orex
    0.07
    DebugEnabled
    0.07
    colar
    0.07
    ublisher
    0.07
    agi
    0.07
    Activations Density 0.006%

    No Known Activations