© 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. 34767
    Prev
    Next
    INDEX
    Explanations

    php code

    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
    åĦ¿çļĦ
    -0.10
    ourke
    -0.09
    ledo
    -0.09
    [href
    -0.09
    ighted
    -0.08
    coln
    -0.08
    HEMA
    -0.08
    ẹp
    -0.08
    .TestCase
    -0.08
     SimpleName
    -0.08
    POSITIVE LOGITS
    ختÙĩ
    0.06
    ed
    0.06
    éĢ®
    0.06
    Ľ
    0.06
    å¥Ķ
    0.06
    ÑģÑĮ
    0.06
     connexion
    0.06
    iskus
    0.06
    б
    0.06
     اÙĦÙĤÙĬ
    0.06
    Activations Density 0.109%

    No Known Activations