© 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. 4104
    Prev
    Next
    INDEX
    Explanations

    partial words/acronyms

    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
    xFFFFFFFF
    -0.28
    .offsetHeight
    -0.23
    _PD
    -0.20
    çĨĶ
    -0.20
     bloginfo
    -0.20
    .epam
    -0.20
    é¼·
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
    xffffffff
    -0.19
    !important
    -0.19
    POSITIVE LOGITS
    DMETHOD
    0.26
    Sharper
    0.23
    sequence
    0.20
    ensely
    0.19
    ;break
    0.19
     '".$
    0.18
    andReturn
    0.18
    并
    0.18
     Implements
    0.17
     Leather
    0.17
    Activations Density 0.006%

    No Known Activations