© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    say simple

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Distribution
    -19.88
    distribution
    -19.63
     distribution
    -19.25
     DISTRIBUT
    -18.63
    _distribution
    -18.38
     distributions
    -17.25
     Distribution
    -16.88
    分布
    -15.63
    区域
    -15.31
    region
    -15.06
    POSITIVE LOGITS
    Sample
    26.50
     Sample
    25.38
     sample
    25.00
     Side
    23.75
    sample
    23.63
    Side
    22.38
    -sample
    21.75
     side
    21.50
    side
    21.13
    (sample
    20.38
    Activations Density 0.052%

    No Known Activations