© 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. 1213
    Prev
    Next
    INDEX
    Explanations

    testing

    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
    аблиÑĨ
    -0.28
    NullException
    -0.27
    ValueCollection
    -0.23
    :'.$
    -0.22
    ãĥµ
    -0.20
    DebugEnabled
    -0.20
    æľĿ
    -0.20
    .scalablytyped
    -0.20
    imageView
    -0.19
    æī¬
    -0.19
    POSITIVE LOGITS
     test
    0.48
    æµĭè¯ķ
    0.40
     tests
    0.40
    test
    0.40
    .test
    0.36
     testing
    0.35
     Test
    0.35
    (test
    0.34
     expected
    0.33
     ÑĤеÑģÑĤ
    0.32
    Activations Density 1.778%

    No Known Activations