© 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. 12244
    Prev
    Next
    INDEX
    Explanations

    question comparison or calculation

    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
     Barros
    -0.08
    anza
    -0.07
    enty
    -0.07
    agate
    -0.07
    azes
    -0.07
    artic
    -0.07
     queried
    -0.07
    odox
    -0.07
    ä¸ĭä¸ĢæĿ¡
    -0.06
    anique
    -0.06
    POSITIVE LOGITS
    rawer
    0.07
    çİ°å®ŀä¸Ń
    0.07
    lems
    0.06
    ints
    0.06
     cause
    0.06
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.06
     plat
    0.06
    äºĶ人
    0.06
    æīįåı¯
    0.06
    adak
    0.06
    Activations Density 0.001%

    No Known Activations