© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    list of items

    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
    lyph
    -0.10
    iado
    -0.09
    ilogy
    -0.09
    iants
    -0.08
    plevel
    -0.08
    <IEnumerable
    -0.08
    shima
    -0.08
    elsius
    -0.08
    .CSS
    -0.08
    enticated
    -0.08
    POSITIVE LOGITS
    ings
    0.11
    -unstyled
    0.10
     halinde
    0.09
    edly
    0.08
    RARY
    0.08
    eners
    0.08
    abyrin
    0.08
    erner
    0.08
     of
    0.08
    ories
    0.08
    Activations Density 0.112%

    No Known Activations