© 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. 2494
    Prev
    Next
    INDEX
    Explanations

    indices and 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
    ,},↵
    -0.21
    :';↵
    -0.20
    koÅĦ
    -0.18
    æĿŁ
    -0.18
    imetype
    -0.18
    çħ§
    -0.18
    élection
    -0.18
     Natürlich
    -0.17
    iran
    -0.17
    Äħż
    -0.17
    POSITIVE LOGITS
    Salvar
    0.21
    ######
    0.20
    ç½ijé¦ĸ页
    0.19
    InBackground
    0.19
    æķ©
    0.18
    ITED
    0.18
     encodeURIComponent
    0.18
    .eof
    0.18
    	UObject
    0.18
    ç¾İåªĴ
    0.18
    Activations Density 0.001%

    No Known Activations