© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    distance and scale measurements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ĭ马
    -0.08
    _UNDER
    -0.08
    榻
    -0.07
    aufs
    -0.07
     NVIC
    -0.07
    ulen
    -0.07
    æī¹
    -0.07
    ethyst
    -0.07
    aporte
    -0.07
    缨
    -0.07
    POSITIVE LOGITS
    è¿ľè·Ŀ离
    0.10
    è¡°åĩı
    0.10
     distance
    0.10
     attenuation
    0.10
     distant
    0.09
     distances
    0.09
    è·Ŀ离
    0.09
    è·ĿéĽ¢
    0.09
    ç¨ĢéĩĬ
    0.09
     attenu
    0.09
    Activations Density 0.004%

    No Known Activations