© 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. 57727
    Prev
    Next
    INDEX
    Explanations

    pdo connection

    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
    ley
    -0.08
    oni
    -0.07
    ke
    -0.07
    ossi
    -0.07
    lands
    -0.07
    tal
    -0.07
    ly
    -0.07
    o
    -0.06
    inggi
    -0.06
    court
    -0.06
    POSITIVE LOGITS
    ´
    0.08
    :///
    0.08
    мок
    0.07
    estos
    0.07
    blk
    0.07
    ddb
    0.07
    ldr
    0.07
    bidden
    0.07
    esus
    0.07
    Ùij
    0.07
    Activations Density 0.449%

    No Known Activations