© 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. 47681
    Prev
    Next
    INDEX
    Explanations

    dating techniques, epidemiological

    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
    oyo
    -0.08
    UCA
    -0.06
    åĴĮ第äºĮ
    -0.06
    åį«
    -0.06
    elsey
    -0.06
     for
    -0.06
    oj
    -0.06
    stek
    -0.06
    بÙĥ
    -0.06
    äºİä¸Ģ
    -0.06
    POSITIVE LOGITS
    _tF
    0.08
    herits
    0.08
    à¸ŀิà¸ĺ
    0.08
    quem
    0.08
    ../../../
    0.08
    å°ıå¹³
    0.07
    ÑĢода
    0.07
    nds
    0.07
    heng
    0.07
    ited
    0.07
    Activations Density 0.034%

    No Known Activations