© 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. 592
    Prev
    Next
    INDEX
    Explanations

    may, can, will

    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
    ++.
    -0.26
    ä¹Łæĺ¯å¾Ī
    -0.24
    okit
    -0.24
    ()=>{↵
    -0.23
    :maj
    -0.23
    utters
    -0.23
    ].'
    -0.23
    cação
    -0.23
    quals
    -0.23
     {}.
    -0.22
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.30
    éĹ®é¢ĺæĺ¯
    0.28
    æķ°æį®æĺ¾ç¤º
    0.27
     may
    0.26
     is
    0.26
     could
    0.26
     will
    0.26
     can
    0.25
     would
    0.25
    æĬ¥åijĬæĺ¾ç¤º
    0.25
    Activations Density 8.407%

    No Known Activations