© 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. 2230
    Prev
    Next
    INDEX
    Explanations

    say "qualification" words

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

    No Comments

    Negative Logits
     rad
    -18.25
    帝
    -17.50
    Demo
    -17.38
    demo
    -16.88
     Rad
    -16.88
    rad
    -16.75
    命
    -16.38
    發
    -16.25
     Dem
    -16.13
     demos
    -16.13
    POSITIVE LOGITS
     Qual
    62.50
     qualification
    60.75
    Qual
    58.50
     qual
    57.00
    资格
    55.00
    qual
    54.50
     qualified
    53.00
    质
    52.50
     qualifications
    50.75
     qualify
    50.50
    Activations Density 0.105%

    No Known Activations