© 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. 569
    Prev
    Next
    INDEX
    Explanations

    gibberish text

    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
    apus
    -0.20
     Ste
    -0.20
    INE
    -0.20
    éĶµ
    -0.19
    _GENERIC
    -0.18
    arie
    -0.18
    ibaba
    -0.18
    filer
    -0.18
     unofficial
    -0.18
     /\.(
    -0.18
    POSITIVE LOGITS
    malink
    0.26
    _uploaded
    0.22
    åħįç¨İ
    0.21
     seiz
    0.21
    ɵ
    0.21
    nyder
    0.21
    (fullfile
    0.20
    ç¡ķ士çłĶ究
    0.20
     potrÃł
    0.20
    ðŁļ«
    0.20
    Activations Density 0.002%

    No Known Activations