© 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. 4381
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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
    Negative Logits
    åľ¨éĩĮéĿ¢
    -0.22
    å¦Ĥæŀľçݩ家
    -0.20
    )viewDidLoad
    -0.20
    ลà¸Ńย
    -0.20
    usterity
    -0.20
    mann
    -0.20
    æİ¥åĬĽ
    -0.19
    人æ°ijæľįåĬ¡
    -0.19
     @"↵
    -0.19
    该游æĪı
    -0.19
    POSITIVE LOGITS
    }elseif
    0.25
    vincial
    0.22
    ç¿Ĭ
    0.22
    нÑģÑĤÑĢÑĥ
    0.20
    аÑĢамеÑĤ
    0.20
    .BufferedReader
    0.20
    setError
    0.20
    ÐļÑĥпиÑĤÑĮ
    0.20
    &o
    0.20
    ncoder
    0.19
    Activations Density 0.001%

    No Known Activations