© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    say 半

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

    No Comments

    Negative Logits
    (req
    -23.25
    	req
    -20.38
     req
    -20.25
    req
    -20.25
    =req
    -20.13
    科技
    -19.75
    configs
    -18.50
    (src
    -18.38
    res
    -18.13
    src
    -17.75
    POSITIVE LOGITS
     sem
    47.25
    (sem
    44.00
     semi
    44.00
    Sem
    42.50
    -sem
    42.00
    semi
    41.75
    半
    40.50
     Sem
    40.25
    sem
    40.00
     Semi
    39.50
    Activations Density 0.062%

    No Known Activations