© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    say success

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     field
    -24.63
    	field
    -22.88
    $field
    -22.50
    场
    -22.25
    FieldName
    -21.63
     Field
    -21.00
    .field
    -20.63
    	Field
    -20.63
    fieldname
    -20.63
    字段
    -20.50
    POSITIVE LOGITS
     formation
    19.63
     Formation
    16.38
    Formation
    16.13
    形成
    15.75
    kte
    15.63
    ugs
    15.38
    入园
    14.69
    indle
    14.50
     flow
    14.38
    anine
    13.88
    Activations Density 0.252%

    No Known Activations