© 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. 37743
    Prev
    Next
    INDEX
    Explanations

    foreign characters or code snippets

    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
    ivé
    -0.07
     tul
    -0.07
    满洲
    -0.07
    ritis
    -0.06
    icza
    -0.06
    icot
    -0.06
    ÑģоÑĤ
    -0.06
    abilia
    -0.06
    embl
    -0.06
    è²Į
    -0.06
    POSITIVE LOGITS
    oción
    0.08
    ean
    0.08
    adne
    0.07
    æľĢç¾İ好çļĦ
    0.07
    æ¾İ
    0.07
    ears
    0.07
    æĹłè¯ģ
    0.07
    ([...
    0.07
    iare
    0.07
     Canti
    0.07
    Activations Density 0.001%

    No Known Activations