© 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. 964
    Prev
    Next
    INDEX
    Explanations

    asking for help

    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
    -Cs
    -0.27
    <Sprite
    -0.27
    gnore
    -0.26
     (![
    -0.26
    .handleError
    -0.26
    usterity
    -0.24
    rippling
    -0.24
    avigator
    -0.23
     (*((
    -0.23
     withStyles
    -0.23
    POSITIVE LOGITS
     automát
    0.28
     splitted
    0.26
     OnTrigger
    0.25
     stuff
    0.24
     gonna
    0.24
     Äijấy
    0.24
     elÅij
    0.24
     acompaña
    0.24
     nr
    0.23
    庸
    0.23
    Activations Density 9.971%

    No Known Activations