© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    say accented letters

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

    No Comments

    Negative Logits
    .det
    -17.25
    det
    -16.25
    工
    -15.63
    媒体
    -15.19
     temp
    -14.81
     media
    -14.75
    出入境
    -14.50
    巨
    -13.81
    Interstitial
    -13.56
     hist
    -13.50
    POSITIVE LOGITS
     �
    60.00
    Ž
    39.75
    Š
    39.00
     š
    36.00
    Ř
    34.00
    Ō
    33.50
    š
    32.75
    ſ
    29.13
     �
    28.13
    Ŵ
    27.25
    Activations Density 0.027%

    No Known Activations