© 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. 38335
    Prev
    Next
    INDEX
    Explanations

    test or sum

    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
    untr
    -0.07
    веÑģ
    -0.06
    оÑģÑĤав
    -0.06
    itud
    -0.06
    çļĦä¸Ģ对
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    дон
    -0.06
    tsy
    -0.06
    fli
    -0.06
     tor
    -0.06
    POSITIVE LOGITS
    åģļå®Į
    0.08
    richt
    0.07
    kori
    0.07
    pper
    0.07
    ebol
    0.07
    çģŃäºĨ
    0.07
    (Return
    0.07
    åłª
    0.07
    ngth
    0.07
    EmailAddress
    0.07
    Activations Density 0.026%

    No Known Activations