© 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. 44536
    Prev
    Next
    INDEX
    Explanations

    demand or needs

    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
    Ø©
    -0.10
    oler
    -0.09
    occhio
    -0.09
    zza
    -0.09
    <|box_end|>
    -0.08
    stants
    -0.08
    enso
    -0.08
    ovn
    -0.08
    owie
    -0.08
    serter
    -0.08
    POSITIVE LOGITS
    lessly
    0.09
    ุม
    0.08
    ات
    0.08
    ÙħÙĨد
    0.08
    s
    0.08
    ergestellt
    0.08
    an
    0.08
    ãĥ³
    0.07
    ì²ĺ
    0.07
    аÑĤÑĮ
    0.07
    Activations Density 0.001%

    No Known Activations