© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14764
    Prev
    Next
    INDEX
    Explanations

    say 1

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ghan
    -21.50
    erval
    -20.13
    ghi
    -18.13
    idge
    -18.13
    ighth
    -18.00
    osity
    -17.50
    rimp
    -17.25
     Seam
    -17.25
    鬣
    -16.88
    SCREEN
    -16.63
    POSITIVE LOGITS
    卓
    18.25
     Buck
    16.25
     drift
    16.00
     Hud
    14.88
     buck
    14.06
    �
    14.00
    Dur
    13.81
     thirty
    13.50
    三百
    13.44
    FLT
    13.38
    Activations Density 0.051%

    No Known Activations