© 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. 426
    Prev
    Next
    INDEX
    Explanations

    structured text

    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
    -scalable
    -0.25
    aeda
    -0.23
    马æĭī
    -0.21
     componentWillMount
    -0.20
    åIJijãģį
    -0.19
     FileType
    -0.19
    ¹Ħ
    -0.19
    éĵĭ
    -0.18
     Raqqa
    -0.18
    onen
    -0.18
    POSITIVE LOGITS
    ;br
    0.27
    elper
    0.25
    emens
    0.23
    byss
    0.22
    (always
    0.22
    untime
    0.22
    .Dto
    0.22
    inspace
    0.21
    yectos
    0.21
    ãİŀ
    0.20
    Activations Density 0.001%

    No Known Activations