© 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. 3203
    Prev
    Next
    INDEX
    Explanations

    say field

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    acd
    -16.38
    槎
    -14.50
     Nhi
    -13.69
    针
    -13.50
     flor
    -13.50
    管委会
    -13.50
    igin
    -13.38
    illé
    -13.31
    anship
    -13.19
    WebRequest
    -13.13
    POSITIVE LOGITS
     field
    104.50
    field
    93.50
     Field
    93.00
    Field
    90.00
    (field
    88.50
    场
    88.00
    -field
    86.50
    	field
    86.50
    _field
    85.50
    .field
    79.50
    Activations Density 0.420%

    No Known Activations