© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14892
    Prev
    Next
    INDEX
    Explanations

    fruit is a

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

    No Comments

    Negative Logits
    amat
    -20.50
    gard
    -18.50
    Sent
    -16.75
    icode
    -16.75
    斗
    -16.38
    unj
    -16.00
    广播
    -16.00
    сад
    -16.00
    Sock
    -15.81
    预算
    -15.81
    POSITIVE LOGITS
    jej
    14.31
    -motion
    13.00
    opoulos
    13.00
    istro
    12.38
    형
    12.31
    olk
    12.19
    'er
    12.13
    ly
    12.00
    АО
    11.88
    hiba
    11.81
    Activations Density 0.073%

    No Known Activations