© 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. 3303
    Prev
    Next
    INDEX
    Explanations

    [statement] => [statement]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (st
    -19.25
    .St
    -17.75
     unst
    -17.63
    	st
    -17.63
    ickness
    -17.25
     Starr
    -17.00
    星座
    -16.88
    st
    -16.50
    lescope
    -16.25
     st
    -16.13
    POSITIVE LOGITS
     statement
    66.50
    statement
    59.75
     Statement
    59.25
    Statement
    58.25
    (statement
    55.25
    	statement
    54.50
    _statement
    53.75
     statements
    49.25
    语
    45.25
    statements
    44.50
    Activations Density 0.104%

    No Known Activations