© 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. 19551
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    à¸£à¸¹à¸Ľ
    -0.10
    ered
    -0.09
    erne
    -0.09
    ########
    -0.09
    ipped
    -0.09
    erings
    -0.09
    erd
    -0.09
    er
    -0.09
    erk
    -0.09
    erve
    -0.09
    POSITIVE LOGITS
    acific
    0.11
    resent
    0.11
    artment
    0.11
    licate
    0.10
    ersistent
    0.10
    rior
    0.10
    ocalypse
    0.10
    olicy
    0.10
    resents
    0.10
    ublish
    0.09
    Activations Density 2.235%

    No Known Activations