© 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. 55039
    Prev
    Next
    INDEX
    Explanations

    via field

    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
    ation
    -0.08
    ting
    -0.08
    mons
    -0.06
    zman
    -0.06
    ushima
    -0.06
    grado
    -0.06
    дне
    -0.06
    terdam
    -0.06
    ville
    -0.06
    çķĻæľī
    -0.06
    POSITIVE LOGITS
    /of
    0.10
    à¸ģาย
    0.09
    pired
    0.09
    ringer
    0.09
    leet
    0.09
    cial
    0.09
    came
    0.08
    lyph
    0.08
    åı¯æ¢¦
    0.08
    racia
    0.08
    Activations Density 0.004%

    No Known Activations