© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3623
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -0.27
    strcasecmp
    -0.23
    usercontent
    -0.22
    çݩ家æľĭåıĭ
    -0.21
    orizontal
    -0.21
    åĪĨæīĭ
    -0.20
    ANE
    -0.20
    Ulus
    -0.20
    âĩ¨
    -0.20
    çį¾
    -0.19
    POSITIVE LOGITS
    éducation
    0.21
    楮
    0.20
    uden
    0.20
    .BLL
    0.19
     MPG
    0.19
    kelas
    0.18
     perf
    0.18
     aest
    0.18
    ä¼İ
    0.18
    centroid
    0.17
    Activations Density 0.001%

    No Known Activations