© 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. 55809
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and 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
    elai
    -0.08
    zit
    -0.08
     minh
    -0.07
    ä¸įæıIJ
    -0.07
    ä¹IJè§Ĥ
    -0.07
    ivic
    -0.07
     erm
    -0.07
    åľĨåľĨçļĦ
    -0.07
    æ´ª
    -0.07
     Fondazione
    -0.07
    POSITIVE LOGITS
    uxe
    0.08
    undu
    0.07
    mock
    0.07
    DRV
    0.07
    £¼
    0.06
    kona
    0.06
    prus
    0.06
    uke
    0.06
    usement
    0.06
     Jama
    0.06
    Activations Density 0.013%

    No Known Activations