© 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. 1063
    Prev
    Next
    INDEX
    Explanations

    say politics

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

    No Comments

    Negative Logits
    蛇
    -19.25
    snake
    -18.75
     saddle
    -16.88
    腹泻
    -16.88
     snake
    -16.38
     snakes
    -16.13
     Hond
    -15.75
     Snake
    -15.69
     trade
    -15.06
     shoes
    -15.06
    POSITIVE LOGITS
     POLIT
    25.63
    政治
    24.50
    polit
    23.13
     politics
    22.13
     politique
    21.25
     Politics
    21.13
     polit
    20.75
     political
    20.38
     DC
    19.88
    political
    19.63
    Activations Density 0.356%

    No Known Activations