© 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. 14413
    Prev
    Next
    INDEX
    Explanations

    say single-digit numbers

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

    No Comments

    Negative Logits
    strup
    -19.75
    oru
    -18.63
    arus
    -18.13
    便利店
    -18.00
    inery
    -17.88
     bedrooms
    -17.88
     hubby
    -17.75
    iciel
    -17.75
     Enumerable
    -17.38
    umper
    -17.25
    POSITIVE LOGITS
    sch
    15.06
     K
    15.00
     fest
    14.69
    fold
    13.44
     Rhe
    13.00
     sc
    12.63
     bil
    12.50
     fel
    12.44
     fasc
    12.44
    K
    12.44
    Activations Density 0.073%

    No Known Activations