© 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. 658
    Prev
    Next
    INDEX
    Explanations

    say "two-letter M abbreviations"

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

    No Comments

    Negative Logits
    尕
    -17.13
    江西
    -17.00
    江西省
    -16.38
    族自治州
    -15.63
    赣
    -15.25
    俄国
    -14.88
    族自治县
    -14.69
    Russia
    -14.50
    泺
    -14.44
    France
    -14.38
    POSITIVE LOGITS
     PM
    70.50
     DM
    66.00
     GM
    66.00
    (pm
    65.00
    PM
    61.75
     BM
    60.75
     CM
    60.50
    (dm
    60.25
     FM
    60.25
    (fm
    58.75
    Activations Density 1.067%

    No Known Activations