© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    say Islamic

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

    No Comments

    Negative Logits
    法兰
    -18.50
    意大利
    -18.13
    EIF
    -17.50
    谌
    -17.38
     Vogue
    -17.00
    张家界
    -16.88
     Hermione
    -16.75
    匈
    -16.63
     Michele
    -16.25
    射击
    -16.13
    POSITIVE LOGITS
    noinspection
    16.63
    tb
    15.63
    枇
    15.44
    斋
    15.38
     سبحانه
    15.19
     Almighty
    15.06
    偈
    14.63
    ǝ
    14.44
    �
    14.44
     Hawai
    14.38
    Activations Density 0.297%

    No Known Activations