© 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. 4054
    Prev
    Next
    INDEX
    Explanations

    CD

    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
    TÃľ
    -0.26
    åIJįåĪĹåīį
    -0.26
    izabeth
    -0.25
    تÙĦÙģزÙĬÙĪÙĨ
    -0.24
    ɵ
    -0.24
    ä¸Ģ个èģĮä¸ļ
    -0.23
    ç§ģæľį
    -0.23
    SMART
    -0.23
     perpetr
    -0.23
    .cloudflare
    -0.23
    POSITIVE LOGITS
    åħīæ»ij
    0.26
     PartialView
    0.22
     "[%
    0.21
     Presence
    0.20
    -datepicker
    0.19
    åĨľåī¯
    0.19
    ãģªãģĦãģĵãģ¨
    0.19
     assaulting
    0.19
     markers
    0.19
    éĻĦ件
    0.19
    Activations Density 0.021%

    No Known Activations