© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2613
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    'gc
    -0.20
     (*)(
    -0.19
    åĢĴåľ¨
    -0.19
    etur
    -0.19
    (*)(
    -0.19
    anky
    -0.19
    دÙĩ
    -0.19
     Unsure
    -0.18
    æ½¢
    -0.18
    åķĨ
    -0.18
    POSITIVE LOGITS
    æ¯ıä¸Ģ个
    0.23
    çŃĮ
    0.21
     Note
    0.21
    notice
    0.21
    note
    0.21
    ocator
    0.21
    注æĦı
    0.21
     note
    0.20
     Notice
    0.20
    Note
    0.20
    Activations Density 0.023%

    No Known Activations