© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    technical terms or names

    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
    .AppendFormat
    -0.24
     MediaTek
    -0.23
    Nguá»ĵn
    -0.23
    .AllowUser
    -0.23
    游æĪıæĬĢå·§
    -0.23
    ÐĦ
    -0.22
    â¬Ĩ
    -0.22
    combe
    -0.22
    âĩĮ
    -0.21
    BOSE
    -0.21
    POSITIVE LOGITS
    åŃĹ
    0.27
    earable
    0.26
    uele
    0.21
    odem
    0.21
    jure
    0.21
    ORIZONTAL
    0.21
    6
    0.20
     startPos
    0.20
    _slider
    0.19
    uckles
    0.19
    Activations Density 0.011%

    No Known Activations