© 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. 4742
    Prev
    Next
    INDEX
    Explanations

    capitalism and economics

    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
    abouts
    -0.08
    een
    -0.08
    UREMENT
    -0.07
    ãĢħãģ®
    -0.07
    ness
    -0.07
    ep
    -0.07
    à¹Ĩ
    -0.07
    eh
    -0.07
    Ø©
    -0.07
    NESS
    -0.07
    POSITIVE LOGITS
    à¸Ļิà¹Īà¸ĩ
    0.10
    ifornia
    0.09
    éĽĦåİļ
    0.09
    иÑĢов
    0.09
    azier
    0.09
    izing
    0.08
    ization
    0.08
    avera
    0.08
    ized
    0.08
    astrophe
    0.08
    Activations Density 0.018%

    No Known Activations