© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    丁

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

    No Comments

    Negative Logits
    'em
    -19.00
    em
    -18.88
    Em
    -18.50
     Em
    -18.50
     em
    -18.38
    /em
    -17.50
    -em
    -17.25
    (em
    -17.00
    	em
    -16.63
     Evolution
    -16.00
    POSITIVE LOGITS
    丁
    87.50
     Dat
    53.50
     dat
    51.00
    (dat
    49.75
    Dat
    47.75
    乙
    42.75
    丙
    42.75
    _dat
    42.75
     dt
    42.25
    dat
    42.00
    Activations Density 0.052%

    No Known Activations