© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    say "ot"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pert
    -19.63
    Mut
    -18.75
     Mat
    -18.63
     Mut
    -17.38
    mut
    -17.00
    腿
    -16.63
    Mat
    -16.50
    徐
    -16.50
     mutual
    -16.38
     Lib
    -16.25
    POSITIVE LOGITS
     pot
    25.88
    Pot
    25.50
    pot
    24.38
     Pot
    23.25
    Mor
    21.75
     Mods
    21.25
     COL
    21.13
     OT
    20.75
     rot
    19.50
     ot
    19.00
    Activations Density 0.219%

    No Known Activations