© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14950
    Prev
    Next
    INDEX
    Explanations

    code symbols

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Latch
    -20.50
    aminer
    -18.13
    莲花
    -17.63
     Ranger
    -17.50
    rats
    -17.38
    圳
    -17.38
    ertation
    -16.75
    rack
    -16.25
    ondheim
    -16.25
    altung
    -16.13
    POSITIVE LOGITS
     Nikol
    15.00
    Fore
    14.94
    魔鬼
    14.88
    Fs
    14.75
    娲
    14.56
    кро
    14.44
    衮
    14.31
    imo
    14.13
    工具
    14.13
     kol
    13.94
    Activations Density 0.105%

    No Known Activations