© 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. 52218
    Prev
    Next
    INDEX
    Explanations

    mass and weight 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
    Negative Logits
    å°¼æĸ¯
    -0.08
     <+
    -0.08
    omon
    -0.08
    çľ·
    -0.07
     [[[
    -0.07
    estad
    -0.07
    νο
    -0.07
    denes
    -0.07
    ä¸ĩå¥Ĺ
    -0.07
    åħ¨ä¼ļ
    -0.07
    POSITIVE LOGITS
    weight
    0.09
    éĩįéĩı
    0.08
    /material
    0.08
    mass
    0.08
     mass
    0.08
     kilograms
    0.08
     маÑģÑģÑĭ
    0.08
    ure
    0.08
     weight
    0.07
    -weight
    0.07
    Activations Density 0.016%

    No Known Activations