© 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. 905
    Prev
    Next
    INDEX
    Explanations

    say “E” ending

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

    No Comments

    Negative Logits
    澳洲
    -16.50
    .tpl
    -16.13
    olo
    -15.31
    OOK
    -14.50
    avin
    -14.44
    农副
    -14.31
     Smarty
    -14.06
    大洋
    -14.00
    HASH
    -13.94
    Sa
    -13.63
    POSITIVE LOGITS
     CE
    64.00
     SE
    61.00
     FE
    60.75
     ME
    59.50
     PE
    58.75
     TE
    58.25
     KE
    57.00
     AE
    56.75
     HE
    56.75
    CE
    56.50
    Activations Density 0.705%

    No Known Activations