© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2011
    Prev
    Next
    INDEX
    Explanations

    say log words

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

    No Comments

    Negative Logits
     Shakespeare
    -33.50
    akespeare
    -22.75
     Chess
    -20.13
     chess
    -19.88
    Chess
    -19.13
    delta
    -18.88
    letter
    -18.63
     delta
    -18.00
    lish
    -17.88
     Delta
    -17.75
    POSITIVE LOGITS
    物流
    18.75
     fluids
    17.25
    物流企业
    16.63
    物流公司
    16.25
     networking
    16.25
    LOG
    15.94
    actories
    15.75
    лог
    15.50
     LOG
    15.50
    DNS
    15.44
    Activations Density 0.091%

    No Known Activations