© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
    pollo
    -0.24
     {č↵č↵č↵
    -0.22
    indsay
    -0.22
    ereotype
    -0.22
     helf
    -0.22
     Gorgeous
    -0.21
     gover
    -0.21
    ungeons
    -0.20
    iets
    -0.20
    (strict
    -0.20
    POSITIVE LOGITS
    æļĩ
    0.20
    jam
    0.20
    éŀł
    0.20
    驳
    0.19
    éĴĪ对æĢ§
    0.19
    è¿ĺå¾Ĺ
    0.19
    èĤ¸
    0.18
     Contr
    0.18
    è¾Ł
    0.18
    _Box
    0.18
    Activations Density 0.001%

    No Known Activations