© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 127
    Prev
    Next
    INDEX
    Explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     èĩªåĬ¨çĶŁæĪIJ
    -0.24
    çĹĤ
    -0.22
     UNSIGNED
    -0.22
    asjon
    -0.21
    -strokes
    -0.21
    -runner
    -0.21
    SION
    -0.20
     sodom
    -0.20
     Pendant
    -0.20
     Aires
    -0.20
    POSITIVE LOGITS
     translateY
    0.25
    addContainerGap
    0.22
    orne
    0.21
     CircularProgress
    0.21
    /cms
    0.20
     acompaña
    0.20
    anford
    0.19
     {-
    0.19
     neg
    0.19
     glVertex
    0.19
    Activations Density 0.434%

    No Known Activations