© 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. 268
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
    严
    -0.22
    stdbool
    -0.20
    oti
    -0.19
     ofApp
    -0.19
     ain
    -0.19
    ozo
    -0.19
    æ¦Ń
    -0.17
     }},↵
    -0.17
     lite
    -0.17
     }}"><
    -0.17
    POSITIVE LOGITS
     çĶŁåij½åij¨æľŁ
    0.23
    )throws
    0.21
    .EventQueue
    0.21
    _whitespace
    0.21
    ")!=
    0.20
     ÐłÐ¾ÑģÑģ
    0.20
    raisal
    0.20
    è·»
    0.20
    upy
    0.20
    éļıåIJİ
    0.20
    Activations Density 0.930%

    No Known Activations