© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2372
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
    vrier
    -0.28
    :".$
    -0.27
    )↵↵↵↵↵↵↵↵
    -0.25
    :normal
    -0.24
    ÐŁÐ¾Ð´ÑĢоб
    -0.24
    ÐŀÑģ
    -0.22
    (___
    -0.22
    [--
    -0.22
    :'.$
    -0.22
    zÄħd
    -0.22
    POSITIVE LOGITS
    å®ŀåĬ¡
    0.24
     commentator
    0.23
     primaryStage
    0.21
    ¤
    0.21
     Law
    0.21
    å¾ĭå¸Ī
    0.20
    Law
    0.20
     lawyer
    0.20
    æĨĶ
    0.20
    findOrFail
    0.20
    Activations Density 0.056%

    No Known Activations