© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3026
    Prev
    Next
    INDEX
    Explanations

    say "放"

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

    No Comments

    Negative Logits
    壬
    -22.75
    戊
    -22.50
    Eth
    -19.13
    丙
    -18.88
    甲
    -18.13
     tet
    -17.88
    乙
    -17.50
    .eth
    -17.38
    eth
    -17.25
    庚
    -17.25
    POSITIVE LOGITS
    放
    46.75
    =pos
    19.88
     pos
    19.88
    放出
    19.75
     var
    18.88
    ,pos
    18.13
    (pos
    18.13
    ,var
    18.00
     rec
    17.88
    变
    17.88
    Activations Density 0.060%

    No Known Activations