© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2859
    Prev
    Next
    INDEX
    Explanations

    light spectrum

    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
    ıģ
    -0.22
    ancock
    -0.21
    æĬ¥æ¡Ī
    -0.20
    BUF
    -0.20
    toISOString
    -0.20
    gaard
    -0.20
    []>↵
    -0.19
    ribly
    -0.18
     overnight
    -0.18
    .Autowired
    -0.18
    POSITIVE LOGITS
     lasers
    0.23
     sunlight
    0.22
    ç´«å¤ĸ
    0.22
    åħī线
    0.22
     ******************************************************************************↵
    0.20
     GÅĤ
    0.19
     Angebot
    0.19
     spectrum
    0.19
    æŁ¥çľĭæĽ´å¤ļ
    0.19
    _TRIANGLES
    0.19
    Activations Density 0.513%

    No Known Activations