© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14997
    Prev
    Next
    INDEX
    Explanations

    time duration

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

    No Comments

    Negative Logits
    eer
    -19.38
    yan
    -18.88
    yer
    -18.63
    yal
    -18.50
    eyer
    -18.00
    yah
    -17.63
    ead
    -17.50
    yers
    -17.38
    ään
    -17.13
    yat
    -17.13
    POSITIVE LOGITS
    cher
    17.13
     McKenzie
    17.00
    ching
    16.88
     dock
    16.25
    strom
    16.13
    三季度
    15.94
     Dawson
    15.13
    汤
    15.13
     Tribute
    15.13
    duck
    15.06
    Activations Density 0.118%

    No Known Activations