© 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. 780
    Prev
    Next
    INDEX
    Explanations

    say "peanut"

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

    No Comments

    Negative Logits
     Dublin
    -25.88
    武汉
    -25.63
    爱尔兰
    -25.25
    武汉市
    -25.13
    珞
    -24.75
    九江
    -24.50
     Irish
    -24.50
    鄂
    -23.75
     Prague
    -22.38
    宜昌
    -22.25
    POSITIVE LOGITS
    花生
    41.00
     Arkansas
    30.88
     peanut
    30.25
     Mississippi
    30.13
     Peanut
    29.25
    ల
    28.00
    �
    27.50
    బ
    27.25
    �
    27.13
    茂名
    26.63
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.