© 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. 1652
    Prev
    Next
    INDEX
    Explanations

    recent

    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
     both
    -0.26
    éĵ©
    -0.26
     either
    -0.25
    第ä¸Ģéĥ¨
    -0.24
    åİĨ代
    -0.24
    éĤ£äºĽ
    -0.23
     everywhere
    -0.23
     any
    -0.22
    Sharper
    -0.22
    ä»»ä½ķå½¢å¼ı
    -0.22
    POSITIVE LOGITS
     recently
    0.46
     Recently
    0.35
    recent
    0.34
    Recently
    0.34
    ðŁĵIJ
    0.32
    âļĹ
    0.30
    ä¸įä¹ħåīį
    0.29
    åģ¶çĦ¶
    0.29
     recent
    0.28
    _recent
    0.28
    Activations Density 8.027%

    No Known Activations