© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1676
    Prev
    Next
    INDEX
    Explanations

    say crops

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

    No Comments

    Negative Logits
    茶
    -58.25
     tea
    -55.25
     Tea
    -52.25
    茶叶
    -50.00
     TE
    -46.00
    tea
    -44.25
     teas
    -44.00
    茶园
    -43.50
    喝茶
    -43.50
    Te
    -43.00
    POSITIVE LOGITS
    angelo
    16.00
    NIC
    15.25
     NIC
    15.13
    onis
    15.13
    iator
    15.00
    Flo
    14.94
     Ballard
    14.75
    (Syntax
    14.50
    POL
    14.31
    /Grid
    14.25
    Activations Density 0.077%

    No Known Activations