© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16360
    Prev
    Next
    INDEX
    Explanations

    say W

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

    No Comments

    Negative Logits
    ��
    -18.25
    тин
    -15.69
    鲠
    -14.38
    岙
    -14.25
     phẩm
    -13.75
    PTY
    -13.69
    oky
    -13.38
     tête
    -13.25
    瑚
    -13.06
     Dund
    -13.00
    POSITIVE LOGITS
    -w
    48.25
    -W
    47.75
    wa
    46.25
    ws
    45.50
    WW
    45.25
    wi
    45.00
    WS
    44.75
     WC
    44.75
    /w
    44.50
    wl
    44.50
    Activations Density 8.107%

    No Known Activations