© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4020
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    alem
    -0.22
    .randomUUID
    -0.20
    ignKey
    -0.20
    éķ¦
    -0.20
    eed
    -0.18
    xCC
    -0.18
    ensors
    -0.18
    -prepend
    -0.18
     Adler
    -0.18
    éĵ£
    -0.17
    POSITIVE LOGITS
     bagi
    0.42
    对äºİ
    0.38
     chez
    0.36
    ä½Ĩ对äºİ
    0.34
    èĢĮ对äºİ
    0.32
     باÙĦÙĨسبة
    0.31
    สำ
    0.30
     for
    0.30
    ä½Ĩæĺ¯å¯¹äºİ
    0.30
    éĢĤçĶ¨äºİ
    0.29
    Activations Density 1.572%

    No Known Activations