© 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. 14780
    Prev
    Next
    INDEX
    Explanations

    say "1"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Hayward
    -17.88
    favorites
    -16.75
    fid
    -16.38
    .fi
    -16.38
     Farr
    -15.81
    fi
    -15.75
    hyp
    -15.25
    -se
    -15.19
    Favorites
    -14.75
    eyer
    -14.69
    POSITIVE LOGITS
    롱
    19.38
    ulin
    19.25
    olin
    18.38
    TouchListener
    18.13
    liner
    18.00
     Dillon
    18.00
    โด
    18.00
    _DLL
    17.88
    rollo
    17.50
    ولة
    17.38
    Activations Density 0.060%

    No Known Activations