© 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. 60061
    Prev
    Next
    INDEX
    Explanations

    cognitive

    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
    pee
    -0.07
    کارÛĮ
    -0.07
    ¾
    -0.07
    nya
    -0.07
     incond
    -0.07
    shire
    -0.07
    微信æī«çłģ
    -0.07
    ãĥĩãĤ£ãĥ³ãĤ°
    -0.07
    quoi
    -0.07
    ëŀĮ
    -0.07
    POSITIVE LOGITS
    åı
    0.09
    itiva
    0.08
    ernen
    0.08
    avanaugh
    0.08
    éĮ¬
    0.08
    ä¹ĭ士
    0.07
    arella
    0.07
    esar
    0.07
    -intensive
    0.07
    esimo
    0.07
    Activations Density 0.016%

    No Known Activations