© 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. 540
    Prev
    Next
    INDEX
    Explanations

    code or symbols

    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
    знаком
    -0.24
     Wander
    -0.21
    itere
    -0.20
     Saunders
    -0.20
     beÄŁen
    -0.20
    赧
    -0.20
    leanor
    -0.20
     Surg
    -0.20
    å»Ļ
    -0.19
     Natürlich
    -0.19
    POSITIVE LOGITS
    ],&
    0.20
    æĪIJæķĪ
    0.19
     kommun
    0.19
    .credit
    0.19
     kosten
    0.18
    (depend
    0.18
    olla
    0.18
    æł¼
    0.18
    樽
    0.18
    ÅĦsk
    0.18
    Activations Density 0.001%

    No Known Activations