© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    say proper nouns

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

    No Comments

    Negative Logits
    conc
    -24.38
    _CONV
    -24.25
     Conc
    -23.38
     conc
    -23.13
    lé
    -22.13
    conv
    -21.63
    /con
    -21.50
    (conv
    -21.13
     kon
    -20.88
    (con
    -20.88
    POSITIVE LOGITS
     Greenwood
    25.13
    青山
    23.88
    安娜
    20.50
     Roose
    20.13
     Johan
    20.00
    堇
    19.63
    路虎
    19.00
    雪山
    18.75
     Cardiff
    18.38
    _blueprint
    18.25
    Activations Density 4.632%

    No Known Activations