© 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. 4028
    Prev
    Next
    INDEX
    Explanations

    bank side

    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
    avel
    -0.08
    imson
    -0.07
    stens
    -0.07
    ynet
    -0.07
    /GL
    -0.07
    .ravel
    -0.07
    ibat
    -0.07
    ãĥĢãĤ¦ãĥ³
    -0.07
    ../../../../
    -0.07
    ottes
    -0.07
    POSITIVE LOGITS
    ä¸Ģ侧
    0.07
     opposite
    0.07
    side
    0.07
     Swing
    0.07
    -side
    0.07
    æĵģ
    0.07
    etz
    0.07
    æĮ¡æĿ¿
    0.06
    æĪªçĦ¶
    0.06
    åģ´
    0.06
    Activations Density 0.008%

    No Known Activations