© 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. 725
    Prev
    Next
    INDEX
    Explanations

    say "John"

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

    No Comments

    Negative Logits
    蚕
    -20.88
    洸
    -16.63
    扬州
    -16.50
    蚌埠
    -16.00
    (dw
    -15.88
     Spartan
    -15.63
    雎
    -15.56
    quete
    -15.50
     Santiago
    -15.31
    岷
    -15.19
    POSITIVE LOGITS
    _CF
    28.63
     John
    28.25
    黄石
    27.25
    约翰
    27.13
    Mal
    26.50
     john
    26.50
     CF
    26.25
     Johns
    26.13
    John
    26.00
    	cf
    25.63
    Activations Density 0.431%

    No Known Activations