© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15765
    Prev
    Next
    INDEX
    Explanations

    say "titles"

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

    No Comments

    Negative Logits
     Shapiro
    -24.25
     Holocaust
    -22.00
     Reagan
    -21.88
     Rosenberg
    -21.88
     Gutenberg
    -21.38
    utenberg
    -21.25
     Lancaster
    -20.25
    橡
    -19.88
     Newtown
    -19.88
     Rosen
    -19.63
    POSITIVE LOGITS
    勋
    19.50
     Duty
    18.75
    �
    18.63
     Spir
    18.00
    役
    17.88
     duty
    17.38
     prince
    17.00
     Prix
    16.38
    Guild
    16.38
     Kin
    16.00
    Activations Density 5.088%

    No Known Activations