© 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. 25598
    Prev
    Next
    INDEX
    Explanations

    later, side, control, simulations

    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
    Boot
    -0.08
    uille
    -0.07
     Boot
    -0.07
    bee
    -0.06
    ddl
    -0.06
     Assistance
    -0.06
    åħ¶ä¸Ĭ
    -0.06
    ä¼ļ被
    -0.06
    ên
    -0.06
    imson
    -0.06
    POSITIVE LOGITS
     nanti
    0.08
    ÑĨен
    0.08
    WARD
    0.08
    adak
    0.07
    _parsed
    0.07
    gambar
    0.07
    WARDS
    0.07
    æĢİä¹ĪäºĨ
    0.07
    öss
    0.07
    ä¸įçĦ¶
    0.07
    Activations Density 0.001%

    No Known Activations