© 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. 3053
    Prev
    Next
    INDEX
    Explanations

    say Eric

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

    No Comments

    Negative Logits
    大发
    -18.88
    DEV
    -18.38
    Dev
    -18.13
     Dev
    -17.50
     Kem
    -16.50
    ooting
    -16.25
    _dev
    -16.13
     Mut
    -16.13
    mut
    -15.88
     mutually
    -15.88
    POSITIVE LOGITS
     Eric
    68.50
    Eric
    63.25
     er
    58.75
     ER
    58.50
    ERIC
    45.75
     Er
    44.50
    ER
    43.75
    eric
    42.75
    (err
    42.00
    (er
    40.25
    Activations Density 0.042%

    No Known Activations