© 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. 832
    Prev
    Next
    INDEX
    Explanations

    say P

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

    No Comments

    Negative Logits
    湘西
    -17.63
    长沙
    -14.69
     mongo
    -14.38
    mongo
    -14.25
     cds
    -14.19
     Karnataka
    -13.81
     Dublin
    -13.56
     mongoose
    -13.50
    垸
    -13.38
     mongodb
    -12.88
    POSITIVE LOGITS
    PA
    58.00
     PA
    57.00
     PG
    51.00
     PN
    50.75
     PF
    50.75
     PB
    50.00
    PF
    49.75
    PG
    48.50
    PB
    48.25
     PD
    48.00
    Activations Density 1.207%

    No Known Activations