© 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. 46704
    Prev
    Next
    INDEX
    Explanations

    textbook or book

    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
    imiter
    -0.09
    itest
    -0.08
    ادÙĩ
    -0.08
    inar
    -0.07
    <|box_end|>
    -0.07
    estr
    -0.07
    acky
    -0.07
    باس
    -0.07
    Ñģпол
    -0.07
    ronym
    -0.07
    POSITIVE LOGITS
    shelf
    0.08
    éĢļãĤĬãģ®
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    à¹Ģลà¹Īม
    0.07
    ä¸Ģæľ¬
    0.06
     cram
    0.06
    åĴĮçłĶ究
    0.06
    ecera
    0.06
    less
    0.06
    à¹ģลà¹īววà¹Īา
    0.06
    Activations Density 0.008%

    No Known Activations