© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    say "pretty"

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

    No Comments

    Negative Logits
    Ben
    -22.13
    (ctx
    -22.00
     Ben
    -22.00
     den
    -21.63
    -den
    -21.50
     Den
    -20.50
    Jul
    -20.50
     δ
    -20.50
     ctx
    -20.38
     denomination
    -20.25
    POSITIVE LOGITS
     mini
    18.63
    Mini
    16.13
     Mini
    15.94
    pretty
    15.50
    ono
    15.25
     pretty
    14.88
    unity
    14.50
    nano
    14.44
    -mini
    14.19
    千万
    14.19
    Activations Density 0.133%

    No Known Activations