© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44290
    Prev
    Next
    INDEX
    Explanations

    Gaussian followed by related concepts

    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
    Negative Logits
     Ñģобой
    -0.09
    tlement
    -0.09
    æķĻäºİ
    -0.08
    تا
    -0.08
    fulness
    -0.08
    доÑĢо
    -0.08
    åıĬéĶĢåĶ®
    -0.08
    ño
    -0.08
    scape
    -0.08
    woÅĤ
    -0.07
    POSITIVE LOGITS
    ly
    0.08
    ized
    0.08
    ÑĮ
    0.07
    ÑĤиÑĩеÑģки
    0.07
    icch
    0.06
    wendungen
    0.06
    nova
    0.06
    culus
    0.06
    -like
    0.06
    ÑĮеÑĤ
    0.06
    Activations Density 0.002%

    No Known Activations