© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    legal and technical document structures

    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
    ers
    -0.12
    ing
    -0.10
    a
    -0.09
    ator
    -0.09
    ic
    -0.09
    çük
    -0.08
    ially
    -0.08
    jų
    -0.08
    д
    -0.08
    house
    -0.08
    POSITIVE LOGITS
    enticated
    0.13
    criptor
    0.09
    à¸ĩ
    0.09
    ÙĦ
    0.09
    ector
    0.09
    mous
    0.09
    ัà¸ĩ
    0.09
    Ø©
    0.09
    erve
    0.09
    dır
    0.09
    Activations Density 0.063%

    No Known Activations