© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1110
    Prev
    Next
    INDEX
    Explanations

    reported speech

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /↵↵↵↵
    -0.33
    ';↵↵↵↵
    -0.23
    bec
    -0.23
     accuses
    -0.23
    å¿ĸ
    -0.23
    SharedPointer
    -0.22
     accuse
    -0.22
    avanaugh
    -0.22
    GridColumn
    -0.22
     blames
    -0.22
    POSITIVE LOGITS
     ArtÃŃculo
    0.29
    åŃ£åIJİ
    0.27
    -initialized
    0.26
    æĽ°
    0.25
     Rencontre
    0.25
    è¿ĶåĽŀæIJľçĭIJ
    0.23
    âĺŀ
    0.23
     CDDL
    0.22
     said
    0.22
    UCCESS
    0.21
    Activations Density 3.152%

    No Known Activations