© 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. 703
    Prev
    Next
    INDEX
    Explanations

    say "Star Trek"

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

    No Comments

    Negative Logits
     SQLITE
    -23.38
     Palestinian
    -21.00
    宝安
    -20.38
    -Israel
    -20.25
    珠海
    -20.13
     Palestinians
    -20.00
     Portugal
    -20.00
     smokers
    -19.88
    .wind
    -19.50
    雨水
    -19.50
    POSITIVE LOGITS
     Star
    27.25
     Trek
    25.50
    Star
    24.00
     Kling
    22.38
     star
    21.25
    crew
    21.00
     STAR
    19.88
     Kirk
    19.63
    star
    19.38
     warp
    19.25
    Activations Density 0.035%

    No Known Activations