© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    discussed

    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
    ..↵↵↵↵
    -0.40
     :↵↵↵↵
    -0.28
     beÄŁen
    -0.27
    ...↵↵↵↵
    -0.26
     ,č↵
    -0.26
    æīĢæīĢ
    -0.26
    esteem
    -0.25
    ï¼ģ↵↵↵↵
    -0.25
    :↵↵↵↵↵↵
    -0.24
    :convert
    -0.24
    POSITIVE LOGITS
    .↵↵
    0.59
    ãĢĤ↵↵
    0.51
    .↵
    0.51
    ãĢĤ↵
    0.45
    .</
    0.36
    ."↵↵
    0.34
    .↵↵↵
    0.34
    ).↵↵
    0.34
    !↵↵
    0.34
    .č↵č↵
    0.34
    Activations Density 13.571%

    No Known Activations