© 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. 63554
    Prev
    Next
    INDEX
    Explanations

    names starting with 'R' or 'C'

    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
    æĢ§è¡Į为
    -0.09
    yan
    -0.08
    sonian
    -0.08
    Å¡em
    -0.08
    ously
    -0.08
    jenja
    -0.08
    ÑıÑģÑĮ
    -0.08
    å±ĭãģķãĤĵ
    -0.08
    گرÛĮ
    -0.07
    ings
    -0.07
    POSITIVE LOGITS
    áĢIJáĢº
    0.11
    cht
    0.11
    ัà¸Ķ
    0.10
     to
    0.10
    à¶Ńà·Ĭ
    0.10
    à¸ķ
    0.10
    çī¹çļĦ
    0.10
    Ł
    0.10
    ckt
    0.09
    áīµ
    0.09
    Activations Density 0.731%

    No Known Activations