© 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. 44765
    Prev
    Next
    INDEX
    Explanations

    empty lines or space

    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
    ä¸įèĪį
    -0.08
    اص
    -0.08
    chants
    -0.08
    евиÑĩ
    -0.08
    rightness
    -0.08
    eil
    -0.07
    dbe
    -0.07
    à¸Ńาย
    -0.07
    dsm
    -0.07
    abbr
    -0.07
    POSITIVE LOGITS
     between
    0.08
    between
    0.07
     spacer
    0.07
     mellem
    0.07
    éĹ´éļĻ
    0.07
     междÑĥ
    0.07
     giữa
    0.07
    éļĶå¼Ģ
    0.07
    _BUFF
    0.07
    _between
    0.07
    Activations Density 0.005%

    No Known Activations