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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    Problems and uncertainty

    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
    благо
    -0.23
    ä¸İæĹ¶ä¿±
    -0.22
    __["
    -0.22
    èĭ«
    -0.21
    åŃ
    -0.21
    ["+
    -0.20
     små
    -0.20
    .getMinutes
    -0.20
    .isSuccessful
    -0.20
    raphics
    -0.20
    POSITIVE LOGITS
    æĸ°æµªå¾®åįļ
    0.22
    Ø£ÙĦÙħ
    0.21
     bro
    0.20
    :"-"`↵
    0.20
    .REACT
    0.19
    _usec
    0.18
     happ
    0.18
    dio
    0.18
    olla
    0.17
    chedules
    0.17
    Activations Density 0.001%

    No Known Activations