© 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. 10503
    Prev
    Next
    INDEX
    Explanations

    expected value

    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
    edata
    -0.08
    ampion
    -0.08
    ê¹IJ
    -0.08
    éļĪ
    -0.08
    gara
    -0.08
    ingan
    -0.08
    å®Ŀå®Ŀ们
    -0.08
    aad
    -0.07
    acap
    -0.07
    ÑĩиÑĤ
    -0.07
    POSITIVE LOGITS
    åĢ¼
    0.09
    iment
    0.07
    -driven
    0.07
    -value
    0.07
    åĢ¼çļĦ
    0.07
    ize
    0.06
    gleich
    0.06
    åĩºå·®
    0.06
    asley
    0.06
    ozy
    0.06
    Activations Density 0.003%

    No Known Activations