© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60899
    Prev
    Next
    INDEX
    Explanations

    SELECT statements in SQL queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»ħ
    -0.08
    å¸ĺ
    -0.07
    å±¥
    -0.07
    èĦļå°ĸ
    -0.07
    ousse
    -0.07
    åİ®
    -0.07
    (function
    -0.07
    rub
    -0.07
    .NoArgsConstructor
    -0.07
    ä¸īä¸ĥ
    -0.07
    POSITIVE LOGITS
     query
    0.10
    æŁ¥è¯¢
    0.10
     DISTINCT
    0.09
     Query
    0.09
     queries
    0.08
    è¯Ńåı¥
    0.08
    .query
    0.08
     sql
    0.08
     SQL
    0.08
     SELECT
    0.08
    Activations Density 0.356%

    No Known Activations