© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    only, just

    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
    .mdl
    -0.21
    .btnCancel
    -0.20
    ******↵↵
    -0.20
     {{--<
    -0.20
    ()>↵
    -0.20
     âĵĺ
    -0.19
    *)_
    -0.19
    :normal
    -0.19
    .btnSave
    -0.19
    ...',↵
    -0.19
    POSITIVE LOGITS
     only
    0.98
    only
    0.92
    Only
    0.90
     Only
    0.88
    åıª
    0.88
     ONLY
    0.85
    _only
    0.82
    _ONLY
    0.81
    åıªæľī
    0.81
    ONLY
    0.74
    Activations Density 1.114%

    No Known Activations