© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14012
    Prev
    Next
    INDEX
    Explanations

    say SQL

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

    No Comments

    Negative Logits
     Grimm
    -17.63
    网络传播
    -17.25
    综艺
    -17.25
     politic
    -16.75
     AppComponent
    -16.63
    礼物
    -16.50
    西装
    -16.50
    葩
    -16.38
    传播
    -16.13
    电台
    -16.00
    POSITIVE LOGITS
     SQL
    45.25
     sql
    43.75
    SQL
    43.00
     database
    42.50
     databases
    41.50
    数据库
    41.50
    _sql
    41.25
    sql
    41.00
     Database
    41.00
    Database
    40.25
    Activations Density 0.652%

    No Known Activations