© 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. 4160
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
     (*((
    -0.24
     fkk
    -0.22
    èĨĬ
    -0.21
    ,Object
    -0.20
    å¾ķ
    -0.19
     полÑĮз
    -0.19
    å®Ŀè´Ŀ
    -0.19
    妪
    -0.19
    åıĤåĬłä¼ļè®®
    -0.18
    ché
    -0.18
    POSITIVE LOGITS
    ><![
    0.22
    ffee
    0.20
    .EventQueue
    0.20
    swire
    0.20
    tility
    0.20
    :');↵
    0.19
    tones
    0.19
    upakan
    0.19
    .offsetWidth
    0.18
     setBackgroundColor
    0.18
    Activations Density 0.011%

    No Known Activations