© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    ending

    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
    æį¢åı¥è¯Ŀ
    -0.32
    女æĢ§æľĭåıĭ
    -0.28
     :↵↵↵↵
    -0.27
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.26
     Marketable
    -0.26
    ]|[
    -0.25
     Unsure
    -0.24
    {↵↵↵
    -0.24
    åĺ£
    -0.23
     Relatives
    -0.22
    POSITIVE LOGITS
     finally
    0.28
    #endregion
    0.25
     ******************************************************************************↵
    0.25
    finally
    0.24
    ä¸īæĺ¯
    0.24
     subparagraph
    0.24
     endregion
    0.23
     Finally
    0.23
     removeObject
    0.23
     negó
    0.23
    Activations Density 2.002%

    No Known Activations