© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1243
    Prev
    Next
    INDEX
    Explanations

    an

    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
    rippling
    -0.25
    enaries
    -0.25
     nächste
    -0.24
    åij£
    -0.23
    تÙĦÙĥ
    -0.23
    åĹIJ
    -0.22
    clé
    -0.22
    gambar
    -0.22
    .Restrict
    -0.22
     Qualität
    -0.22
    POSITIVE LOGITS
    ther
    0.31
    ROID
    0.29
    FOX
    0.28
     ;↵↵↵
    0.28
    cestor
    0.27
    ÐŁÐ¾Ð´ÑĢобнее
    0.26
    âĨ©
    0.26
    ÄĴ
    0.24
    -Owned
    0.24
    inburgh
    0.24
    Activations Density 0.403%

    No Known Activations