© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    the number one

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

    No Comments

    Negative Logits
    aminer
    -17.88
    ardy
    -17.50
    orc
    -17.50
    (arc
    -17.00
    borg
    -16.50
     Hernandez
    -16.38
    inery
    -16.25
    inent
    -16.25
    pawn
    -16.00
    焚烧
    -15.88
    POSITIVE LOGITS
    Dou
    16.38
     Douglas
    14.81
    ea
    14.13
    etsk
    14.13
    -e
    14.06
     Dou
    13.56
    esse
    13.38
    EA
    13.38
    GU
    13.31
    esome
    13.13
    Activations Density 0.067%

    No Known Activations