© 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. 2894
    Prev
    Next
    INDEX
    Explanations

    say "慈"

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

    No Comments

    Negative Logits
     Propel
    -17.75
    贵阳
    -17.00
    Vec
    -15.75
    Meteor
    -15.44
    滍
    -15.25
    Hex
    -14.88
     Segment
    -14.56
    南昌
    -14.56
    Quant
    -14.50
    芗
    -14.50
    POSITIVE LOGITS
    慈
    46.50
    cert
    25.38
     certs
    22.25
    (cert
    21.63
     Kat
    21.25
     cert
    20.88
    Cert
    19.88
     Cert
    19.63
    CERT
    19.50
    _CERT
    19.38
    Activations Density 0.024%

    No Known Activations