© 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. 155
    Prev
    Next
    INDEX
    Explanations

    US legal contexts

    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
     clearColor
    -0.20
    .dw
    -0.19
    (*)(
    -0.19
    .Hosting
    -0.19
    _dropout
    -0.18
    ä¸įåĩº
    -0.18
     Comey
    -0.18
    ]("
    -0.18
    æĺİçĻ½
    -0.18
    _dw
    -0.18
    POSITIVE LOGITS
     v
    0.35
    =v
    0.24
    >();
    0.22
     Garlic
    0.21
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.21
    é¹£
    0.21
    *v
    0.21
    彩ç¥ŀ
    0.20
    +v
    0.20
     fierc
    0.20
    Activations Density 0.333%

    No Known Activations