© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14694
    Prev
    Next
    INDEX
    Explanations

    say and

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BR
    -19.38
    BR
    -18.63
     LE
    -18.38
    LEC
    -17.75
    brick
    -16.88
    DIG
    -16.75
    北汽
    -16.38
    PL
    -14.94
     Brick
    -14.88
     pick
    -14.69
    POSITIVE LOGITS
    yles
    17.00
     Kardash
    16.75
    tv
    16.50
    kes
    16.13
    tte
    15.88
    xee
    15.88
    köp
    15.88
    rary
    15.56
    rone
    15.44
    rss
    15.38
    Activations Density 0.002%

    No Known Activations