© 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. 15413
    Prev
    Next
    INDEX
    Explanations

    say surname

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

    No Comments

    Negative Logits
    勋
    -19.63
     Spir
    -19.38
     Duty
    -18.88
    �
    -18.63
     prince
    -17.75
     duty
    -17.38
    Guild
    -17.38
    役
    -17.25
    团长
    -17.13
    gx
    -16.75
    POSITIVE LOGITS
     Shapiro
    23.38
     Rosenberg
    22.13
     Holocaust
    21.00
     Gutenberg
    20.63
    utenberg
    20.38
     Reagan
    20.38
     Newtown
    19.13
    橡
    19.13
     Rosen
    19.00
     Lancaster
    18.88
    Activations Density 5.130%

    No Known Activations