© 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. 557
    Prev
    Next
    INDEX
    Explanations

    news headlines

    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
    iếu
    -0.24
    åįĬ导
    -0.23
    ivité
    -0.21
    isure
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
     )]↵
    -0.20
    slaught
    -0.20
    abyrinth
    -0.20
    atomy
    -0.20
    AXB
    -0.20
    POSITIVE LOGITS
    éļ¾æĢª
    0.21
    å§Ĭ妹
    0.20
    vero
    0.20
    Col
    0.20
    èĴ´
    0.20
    andan
    0.19
    交éĻħ
    0.19
    主ä¸ļ
    0.19
    emi
    0.19
    تص
    0.18
    Activations Density 0.001%

    No Known Activations