© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3291
    Prev
    Next
    INDEX
    Explanations

    definition phrases

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    院士
    -17.88
     submar
    -16.88
    bone
    -16.88
    民警
    -16.75
     bone
    -16.75
     backlight
    -16.75
     teeth
    -16.50
     graffiti
    -16.25
     Teeth
    -16.25
    _subnet
    -15.94
    POSITIVE LOGITS
    (cl
    15.94
     Lancaster
    14.00
    bell
    13.50
     Psychic
    13.50
    修
    13.38
     Cy
    13.31
    巳
    13.25
    편
    13.19
     latino
    13.19
     latin
    13.13
    Activations Density 0.272%

    No Known Activations