© 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. 3584
    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
    URLException
    -0.23
     поÑĩем
    -0.22
    !(:
    -0.21
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
    incinn
    -0.20
    .RichTextBox
    -0.20
    rawtypes
    -0.20
    inally
    -0.20
    etically
    -0.19
    .EventArgs
    -0.19
    POSITIVE LOGITS
    buat
    0.21
     ".";↵
    0.20
     medida
    0.19
    ìĺ´
    0.18
    æŧ
    0.18
     UCHAR
    0.18
     exercitation
    0.18
    icens
    0.18
    RESSED
    0.18
    WR
    0.18
    Activations Density 0.000%

    No Known Activations