© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    词

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

    No Comments

    Negative Logits
    词
    -42.00
    詞
    -35.50
     word
    -34.50
    Word
    -32.25
    word
    -32.25
    -word
    -32.25
    _WORD
    -32.00
    _word
    -31.38
     Word
    -31.00
     words
    -30.88
    POSITIVE LOGITS
     Italians
    16.75
    itto
    15.94
    索尼
    15.75
    土壤
    15.38
    mount
    15.19
     SMTP
    15.13
     Georgia
    15.06
    bau
    14.88
    lle
    14.81
    alu
    14.75
    Activations Density 0.058%

    No Known Activations