© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 553
    Prev
    Next
    INDEX
    Explanations

    say "COM"

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

    No Comments

    Negative Logits
    四川
    -31.38
    四川省
    -30.88
    泸州
    -28.13
    川
    -26.50
     California
    -25.88
     RT
    -24.88
     Californ
    -24.13
    California
    -23.88
    天府
    -23.75
     Sacramento
    -23.00
    POSITIVE LOGITS
     CM
    29.63
    CM
    29.38
     Somali
    26.00
     Somalia
    25.88
     Camden
    25.38
    临沂
    25.25
    (COM
    24.25
     COM
    24.25
     CMP
    24.00
    (cm
    23.75
    Activations Density 0.110%

    No Known Activations