© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    course

    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
    ç«ŁçĦ¶
    -0.31
     perhaps
    -0.27
    æĪĸ许
    -0.26
    perhaps
    -0.26
    çĶļèĩ³
    -0.25
    åıįèĢĮ
    -0.25
     actually
    -0.24
    actually
    -0.24
    maybe
    -0.24
     maybe
    -0.23
    POSITIVE LOGITS
    nyder
    0.29
     obviously
    0.29
    å°ijä¸įäºĨ
    0.28
    å½ĵçĦ¶
    0.27
    utenberg
    0.26
    occan
    0.26
    kker
    0.25
    èĩªçĦ¶æĺ¯
    0.24
    å½ĵçĦ¶æĺ¯
    0.24
     obvious
    0.24
    Activations Density 0.269%

    No Known Activations