© 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. 16358
    Prev
    Next
    INDEX
    Explanations

    say "pol"

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

    No Comments

    Negative Logits
    鹫
    -21.75
    庆典
    -20.75
    开封
    -20.75
     Lucifer
    -20.63
    firefox
    -20.38
    香菇
    -20.38
    庆祝
    -19.38
    景德
    -19.00
    烟囱
    -18.75
     Panc
    -18.63
    POSITIVE LOGITS
    pol
    24.00
    jq
    22.00
     jq
    21.88
     pol
    21.13
    Pol
    21.00
     Pol
    21.00
    (jq
    20.88
    -pol
    20.75
     POL
    20.63
    POL
    20.63
    Activations Density 5.235%

    No Known Activations