© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    顾客

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

    No Comments

    Negative Logits
    	tab
    -18.13
    mil
    -17.88
     ver
    -16.13
    integr
    -15.88
    (client
    -15.81
    tab
    -15.63
    client
    -15.56
     nett
    -15.38
    (tab
    -15.38
    proposal
    -15.31
    POSITIVE LOGITS
    顾客
    42.50
    (pat
    30.63
     Pat
    30.63
    Pat
    29.88
    .pat
    28.63
    顧
    27.88
     pat
    26.38
    _pat
    25.50
     PAT
    25.38
    pat
    25.25
    Activations Density 0.033%

    No Known Activations