© 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. 2456
    Prev
    Next
    INDEX
    Explanations

    code/programming elements

    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
    راÙħ
    -0.21
    uyến
    -0.21
    ******č↵
    -0.21
     Canadiens
    -0.20
    ivant
    -0.20
    itat
    -0.19
    ionale
    -0.19
    lesia
    -0.19
    -Ta
    -0.18
    éĻĦåĬł
    -0.18
    POSITIVE LOGITS
     seins
    0.21
    )){↵↵
    0.20
    .parseFloat
    0.20
    å½ĵåľº
    0.20
     "[%
    0.19
    ç±¼
    0.19
    åľ¨çİ°åľº
    0.19
    贯穿
    0.18
    æ³Ľ
    0.18
    çĶ¦
    0.18
    Activations Density 0.027%

    No Known Activations