© 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. 27950
    Prev
    Next
    INDEX
    Explanations

    parameterization

    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
    edException
    -0.08
    neiden
    -0.07
    liness
    -0.07
    itzen
    -0.07
    ervisor
    -0.07
    erness
    -0.07
    ×ĵ×Ļ×Ŀ
    -0.07
    ãĥ¼ãĥĬ
    -0.07
    -ton
    -0.07
    strom
    -0.07
    POSITIVE LOGITS
     ulang
    0.10
    etrize
    0.09
    æĢ§åľ°
    0.08
    idou
    0.08
    ically
    0.08
    ungan
    0.07
    aggi
    0.07
    æĢ§å¼º
    0.07
    gle
    0.07
     módon
    0.07
    Activations Density 0.007%

    No Known Activations