© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    AD followed by P or H

    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
    iard
    -0.07
     Lag
    -0.07
    ingan
    -0.07
    rss
    -0.07
    ilig
    -0.07
    ķĮ
    -0.07
    ame
    -0.07
    åįĩåĪĿ
    -0.07
    /rss
    -0.07
     INN
    -0.07
    POSITIVE LOGITS
    okane
    0.08
    éĿĸ
    0.07
    å¡ļ
    0.07
    sons
    0.07
    avanaugh
    0.07
    otov
    0.07
    åIJĦåľ°åĮº
    0.07
    æĸ¹æīį
    0.07
    ÑģÑĥÑĢ
    0.07
    untime
    0.07
    Activations Density 0.002%

    No Known Activations