© 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. 4179
    Prev
    Next
    INDEX
    Explanations

    Technical specific jargon

    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
     Swe
    -0.21
    longleftrightarrow
    -0.20
    åħĭåĪ¶
    -0.20
    .sav
    -0.19
    ayas
    -0.18
    æ²»çIJĨ
    -0.18
     namoro
    -0.18
    主åĬ¨æĢ§
    -0.18
    Qual
    -0.18
    l
    -0.17
    POSITIVE LOGITS
    æľīæľŁå¾Ĵ
    0.30
    åĢŀ
    0.25
    intégr
    0.23
    akhir
    0.23
    -Cs
    0.23
    wiÄĻks
    0.22
     ifdef
    0.22
    akter
    0.22
    éĴ«
    0.22
    å§Ķç»Ħç»ĩ
    0.22
    Activations Density 0.001%

    No Known Activations