© 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. 1283
    Prev
    Next
    INDEX
    Explanations

    O names

    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
    __':č↵
    -0.24
     Lump
    -0.23
    emetery
    -0.22
    zbollah
    -0.22
    檩
    -0.22
    ìĮį
    -0.21
     bénéficie
    -0.21
    NAMESPACE
    -0.21
    :async
    -0.21
    (iOS
    -0.21
    POSITIVE LOGITS
    ohon
    0.20
    æīĭèĦļ
    0.20
     bú
    0.19
    UIL
    0.19
    éli
    0.18
    ä¸ĩåįĥ
    0.18
    вол
    0.18
    IDDEN
    0.18
    CLU
    0.17
     Wig
    0.17
    Activations Density 0.002%

    No Known Activations