© 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. 52221
    Prev
    Next
    INDEX
    Explanations

    relativistic

    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
    imizer
    -0.09
    lesh
    -0.09
    ingang
    -0.09
    éĺħè¯»æľ¬æĸĩåīį
    -0.09
    rlen
    -0.08
     radik
    -0.08
    erah
    -0.08
    ила
    -0.08
    OrUpdate
    -0.08
    ilton
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    istic
    0.10
    idad
    0.07
    izing
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    mente
    0.07
    å§
    0.07
    ally
    0.07
    ian
    0.07
    ists
    0.07
    Activations Density 0.004%

    No Known Activations