© 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. 545
    Prev
    Next
    INDEX
    Explanations

    technical or 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
    illez
    -0.19
    _SECTION
    -0.19
    .TabStop
    -0.19
     barric
    -0.18
    .bumptech
    -0.18
    .FindAsync
    -0.18
    嵯
    -0.18
    estroy
    -0.18
    å¿ħä¸įåı¯
    -0.18
     datum
    -0.17
    POSITIVE LOGITS
    ihanna
    0.26
    åłī
    0.23
     Boeh
    0.22
    {!!
    0.22
     Decompiled
    0.22
    çIJİ
    0.22
     Moines
    0.21
    ç¡ļ
    0.21
    []{↵
    0.20
    riott
    0.20
    Activations Density 0.001%

    No Known Activations