© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    say <|im_start|>

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (phone
    -14.31
    ichen
    -13.69
     cu
    -13.44
     digits
    -13.31
    cod
    -13.06
     light
    -13.00
    法
    -13.00
    Phot
    -12.94
    light
    -12.88
    UCK
    -12.50
    POSITIVE LOGITS
    ไหล
    17.38
    kest
    16.88
    Instrument
    16.63
    жи
    16.25
    代表团
    16.25
    instrument
    15.63
     Instruments
    15.38
    ぞ
    15.31
     instruments
    15.25
     Ar
    14.88
    Activations Density 0.012%

    No Known Activations