© 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. 16025
    Prev
    Next
    INDEX
    Explanations

    say "Pro"

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

    No Comments

    Negative Logits
    墨
    -17.50
    aurant
    -17.00
    瘪
    -16.63
     FEMA
    -15.94
    嫣
    -15.88
    籁
    -15.88
    毒
    -15.63
     Gul
    -15.50
    烟花
    -15.38
    鲜艳
    -15.38
    POSITIVE LOGITS
     Pro
    68.00
    Pro
    64.00
    pro
    63.50
    (pro
    62.75
    PRO
    62.50
     PRO
    62.00
    _Pro
    61.00
    -Pro
    60.50
    .pro
    60.50
    _pro
    60.00
    Activations Density 0.407%

    No Known Activations