© 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. 15358
    Prev
    Next
    INDEX
    Explanations

    say "1"

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

    No Comments

    Negative Logits
     Sinclair
    -20.88
    ibs
    -20.25
     Sloan
    -19.63
    shan
    -18.63
    荪
    -18.38
    ilian
    -18.25
    ibal
    -18.25
    lian
    -18.13
    nim
    -17.75
     Hib
    -17.50
    POSITIVE LOGITS
     Cold
    14.94
    ogle
    14.88
    供图
    14.75
    стой
    14.31
    俄乌
    14.25
    诃
    14.25
    三代
    14.13
     thermo
    14.06
    中科
    14.00
    stead
    13.88
    Activations Density 0.081%

    No Known Activations