© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    say "log"

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

    No Comments

    Negative Logits
     Eating
    -29.25
     eating
    -28.25
     Eat
    -27.50
     eat
    -27.25
    Eat
    -26.00
    食用
    -24.88
    吃
    -24.50
    的食物
    -24.50
     eats
    -23.63
    食物
    -23.13
    POSITIVE LOGITS
     Log
    16.75
     Porter
    16.63
    Log
    16.63
    _log
    16.13
     log
    15.44
    fuel
    15.25
    istra
    15.13
     logarith
    15.00
     spiritual
    15.00
     pol
    14.94
    Activations Density 0.114%

    No Known Activations