© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15526
    Prev
    Next
    INDEX
    Explanations

    say u

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

    No Comments

    Negative Logits
    泾
    -17.25
    洋洋
    -16.00
    邴
    -16.00
    沣
    -16.00
    丐
    -15.13
    cade
    -15.06
    湃
    -14.88
    렉
    -14.88
    秦皇
    -14.88
    嫘
    -14.81
    POSITIVE LOGITS
    ᴜ
    36.00
    PU
    35.25
    CU
    34.75
    uum
    34.50
    u
    34.50
    uc
    34.00
    乌
    34.00
    𝑢
    34.00
    ｕ
    34.00
    -u
    33.50
    Activations Density 8.240%

    No Known Activations