© 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. 13140
    Prev
    Next
    INDEX
    Explanations

    you followed by modal verbs

    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
    ity
    -0.08
    irk
    -0.07
    æľīæĦıä¹ī
    -0.07
    URITY
    -0.07
    æľīæĦıä¹īçļĦ
    -0.07
    .au
    -0.07
    tıģı
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    uits
    -0.06
    æĽ´ä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    arana
    0.09
    kses
    0.08
    Ñģловно
    0.08
    fulness
    0.08
    dden
    0.07
    fran
    0.07
    onex
    0.07
    妨
    0.07
    cred
    0.07
    ×ij×¢
    0.07
    Activations Density 0.086%

    No Known Activations