© 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. 2821
    Prev
    Next
    INDEX
    Explanations

    say ant

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

    No Comments

    Negative Logits
    发
    -21.63
    prop
    -18.38
    -prop
    -17.88
    大发
    -17.25
    	prop
    -17.13
    [prop
    -16.50
    (prop
    -16.13
    [src
    -16.00
     deriv
    -15.88
     Moto
    -15.88
    POSITIVE LOGITS
    Ant
    49.25
     ANT
    47.50
    南极
    47.00
     Ant
    46.00
     ant
    45.00
     Antar
    42.00
    _ant
    42.00
     polar
    40.75
     Antarctica
    40.50
    ant
    39.75
    Activations Density 0.043%

    No Known Activations