© 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. 44746
    Prev
    Next
    INDEX
    Explanations

    range and distance

    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
    æīĭèĦļ
    -0.07
    ë¦ĩ
    -0.07
    _TERMIN
    -0.07
    leans
    -0.07
    ç¿»äºĨ
    -0.07
    转åĩº
    -0.07
     meta
    -0.07
    ToStr
    -0.07
    æĵ
    -0.07
     баÑĤ
    -0.06
    POSITIVE LOGITS
     distance
    0.17
     distances
    0.17
     Distance
    0.17
    è·ĿéĽ¢
    0.17
    è·Ŀ离
    0.16
    çļĦè·Ŀ离
    0.16
    è¿ijè·Ŀ离
    0.16
    distance
    0.16
    -distance
    0.16
    Distance
    0.16
    Activations Density 0.100%

    No Known Activations