© 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. 531
    Prev
    Next
    INDEX
    Explanations

    code or technical

    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
    zelf
    -0.29
     ($("#
    -0.23
    dle
    -0.22
    éªł
    -0.22
    cité
    -0.21
    .ImageAlign
    -0.19
    andre
    -0.18
     Stephan
    -0.18
    åĪ©çī©
    -0.18
    ×¢×ijר×Ļת
    -0.18
    POSITIVE LOGITS
    emax
    0.21
    	throws
    0.19
    @show
    0.19
    _nombre
    0.19
    thumbs
    0.19
    são
    0.19
    åĬłå·¥åİĤ
    0.19
    .appspot
    0.18
    åķģ
    0.18
    _shuffle
    0.18
    Activations Density 0.001%

    No Known Activations