© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    say 6

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     solution
    -24.38
     Solution
    -23.25
    点
    -23.00
     point
    -23.00
    Solution
    -22.13
    solution
    -21.75
    point
    -21.00
     Point
    -20.88
    Point
    -20.63
     SOLUTION
    -19.88
    POSITIVE LOGITS
    行业
    21.63
    行業
    20.38
    行业的
    18.00
    汽车行业
    17.75
    镇
    17.38
    ExecutionContext
    17.25
     State
    17.13
    等行业
    17.00
    行业发展
    17.00
    TagName
    17.00
    Activations Density 0.312%

    No Known Activations