© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48430
    Prev
    Next
    INDEX
    Explanations

    Lewis followed by acid, rats, or possession

    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
    tings
    -0.08
    imits
    -0.08
    stead
    -0.07
    lev
    -0.07
    kor
    -0.07
    itch
    -0.07
    odelist
    -0.07
    次çļĦ
    -0.07
    let
    -0.07
    earer
    -0.07
    POSITIVE LOGITS
    ruk
    0.07
    .nasa
    0.07
    óÅĤ
    0.07
    bauer
    0.07
    dan
    0.07
    åĴĮèĥ½åĬĽ
    0.07
    cape
    0.07
    หมายà¸Ħวาม
    0.07
    .pad
    0.07
    (es
    0.07
    Activations Density 0.003%

    No Known Activations