© 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. 64932
    Prev
    Next
    INDEX
    Explanations

    code blocks with definitions

    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
    osl
    -0.07
    amol
    -0.07
    cze
    -0.07
    æĥħ人
    -0.07
    åIJij导
    -0.07
    fique
    -0.07
    pieces
    -0.07
    æĻ°
    -0.07
    μαν
    -0.07
    uptools
    -0.06
    POSITIVE LOGITS
    undy
    0.07
    éĩijæ²Ļ
    0.07
    èĢĮæĺĵ
    0.07
    夸
    0.06
    æĢĢ
    0.06
    anser
    0.06
    ç¼®
    0.06
    érir
    0.06
    æĮģ
    0.06
    .SC
    0.06
    Activations Density 0.093%

    No Known Activations