© 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. 35009
    Prev
    Next
    INDEX
    Explanations

    subset

    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
    pha
    -0.08
    blatt
    -0.08
    ppure
    -0.08
    psilon
    -0.08
    iad
    -0.08
    illes
    -0.08
    idup
    -0.08
    eri
    -0.08
    levant
    -0.08
    brids
    -0.07
    POSITIVE LOGITS
    ively
    0.10
    ï¸İ
    0.09
    ness
    0.09
    ï¸ı
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    /out
    0.07
    но
    0.07
    ÙĪا
    0.07
    lay
    0.07
    à¸ģารà¸ĵà¹Į
    0.07
    Activations Density 0.002%

    No Known Activations