© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15011
    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
    堰
    -22.63
    oir
    -20.88
    ois
    -20.13
     Bair
    -18.88
     Sour
    -18.75
     Sears
    -18.50
     Gord
    -18.00
     Mori
    -17.75
    帽
    -17.63
    -grey
    -17.38
    POSITIVE LOGITS
     Phelps
    19.00
     ROC
    18.63
    Spider
    17.88
     Robin
    17.88
    edTextBox
    17.75
     Brooke
    17.75
     robin
    17.75
    铧
    17.63
    乒乓
    17.63
    蜕
    17.63
    Activations Density 1.287%

    No Known Activations