© 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. 779
    Prev
    Next
    INDEX
    Explanations

    non-negative, ordinary, gram-positive

    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
    osz
    -0.09
    utenberg
    -0.08
    æݥ踵
    -0.07
    ocoder
    -0.07
    EAR
    -0.07
    isodes
    -0.07
    æī¹åĩĨåIJİ
    -0.07
    AGIC
    -0.07
    adeiras
    -0.07
    ocode
    -0.07
    POSITIVE LOGITS
    æĻ®éĢļ
    0.07
    ated
    0.07
    åħįåĨł
    0.07
    /non
    0.07
    èªī
    0.06
    éĥ½è¡Į
    0.06
     ordinary
    0.06
     Toda
    0.06
    æĻ®éĢļçļĦ
    0.06
    ren
    0.06
    Activations Density 0.508%

    No Known Activations