© 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. 623
    Prev
    Next
    INDEX
    Explanations

    say "direction" words

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

    No Comments

    Negative Logits
     Tas
    -22.25
    泺
    -21.13
     Montana
    -21.00
    麦
    -20.63
     Tasmania
    -20.63
     Wisconsin
    -20.38
    牦
    -19.75
     chinese
    -19.38
     Icelandic
    -19.00
     Carlson
    -18.88
    POSITIVE LOGITS
     West
    23.13
    东
    22.25
    West
    22.13
     Raleigh
    21.88
    西
    21.63
     Naples
    21.63
    east
    21.38
    -MM
    21.38
     RT
    21.00
    东北
    21.00
    Activations Density 0.372%

    No Known Activations