© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15443
    Prev
    Next
    INDEX
    Explanations

    say delete

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

    No Comments

    Negative Logits
    流淌
    -19.50
    scrollTop
    -18.38
    adin
    -17.88
    hatt
    -17.38
    ighb
    -17.25
    bio
    -16.88
    yntax
    -16.50
     competitions
    -16.38
    ophilia
    -16.38
     Latitude
    -16.13
    POSITIVE LOGITS
     delete
    44.75
    删除
    44.25
     deleting
    43.25
     deletion
    42.50
     deletes
    42.00
    delete
    41.00
     deleted
    40.25
     Deletes
    40.25
    DELETE
    40.00
    (delete
    39.75
    Activations Density 0.222%

    No Known Activations