© 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. 3095
    Prev
    Next
    INDEX
    Explanations

    astronomy

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Funeral
    -18.50
     Pension
    -17.75
    _STYLE
    -17.25
    商户
    -17.00
    	style
    -17.00
     Texans
    -16.88
     тек
    -16.50
     enterprise
    -16.50
     Kund
    -16.50
     Style
    -16.38
    POSITIVE LOGITS
    ml
    15.31
    棒
    14.69
    核心
    14.63
     Tracks
    14.44
    壳
    14.44
    _cm
    14.31
    uci
    14.19
    MS
    13.81
    (ml
    13.81
    ms
    13.75
    Activations Density 0.061%

    No Known Activations