© 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. 2264
    Prev
    Next
    INDEX
    Explanations

    shopping

    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
     acompaña
    -0.23
    (',',$
    -0.21
    åį³
    -0.20
    åıĭæĥħéĵ¾æİ¥
    -0.20
     therefore
    -0.20
     cellForRowAtIndexPath
    -0.20
    são
    -0.20
    _putchar
    -0.20
     ÙĪباÙĦتاÙĦÙĬ
    -0.19
    ICollectionView
    -0.18
    POSITIVE LOGITS
    .IsNullOr
    0.22
    è¿ĺæľīä¸ĢäºĽ
    0.22
     });↵↵↵↵
    0.21
    izza
    0.20
    "';
    0.20
    angu
    0.19
     поÑĩем
    0.19
    strup
    0.19
    "+"
    0.19
    *)_
    0.19
    Activations Density 0.716%

    No Known Activations