© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols like cdot

    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
    иÑģÑĥ
    -0.11
    ÙĪÙĬا
    -0.09
     Verka
    -0.09
    riad
    -0.09
    -spot
    -0.09
    ائب
    -0.09
     milion
    -0.08
     Certif
    -0.08
     Concep
    -0.08
    flas
    -0.08
    POSITIVE LOGITS
     USSR
    0.07
     Herrn
    0.06
     Dy
    0.06
    fr
    0.06
    æ½®
    0.06
     R
    0.06
    æĬķ稿
    0.06
     *
    0.06
     II
    0.05
     \
    0.05
    Activations Density 0.153%

    No Known Activations