© 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. 1223
    Prev
    Next
    INDEX
    Explanations

    the

    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
    olicited
    -0.28
    äºĨåįĬ天
    -0.25
    -ranked
    -0.25
    äºĨ好å¤ļ
    -0.24
     sublic
    -0.22
    幸好
    -0.21
    æĪĸ許
    -0.21
     acompaña
    -0.21
     ("<
    -0.21
    çĽ¸ä¿¡å¤§å®¶
    -0.21
    POSITIVE LOGITS
    /↵↵↵↵
    0.43
     same
    0.41
    ses
    0.39
     latter
    0.31
     entire
    0.30
     following
    0.29
    anine
    0.29
    /ion
    0.28
    tas
    0.28
    ./(
    0.28
    Activations Density 3.730%

    No Known Activations