© 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. 7006
    Prev
    Next
    INDEX
    Explanations

    base followed by code or description keywords

    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
    -0.11
    天边
    -0.09
    soever
    -0.09
    zsche
    -0.09
    åĬłæĭ¿å¤§
    -0.08
    -thirds
    -0.08
    Ø©
    -0.08
    पà¥Ĥरà¥įण
    -0.08
    ëĭĿ
    -0.08
    orio
    -0.08
    POSITIVE LOGITS
    volent
    0.09
    ราà¸ģ
    0.09
    iblio
    0.08
    adona
    0.08
    ward
    0.08
    vÄĵ
    0.08
    iblioteca
    0.08
    plate
    0.08
    elor
    0.08
    éĽĦåİļçļĦ
    0.08
    Activations Density 0.055%

    No Known Activations