© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    stered
    -0.21
    ADIUS
    -0.20
    DMIN
    -0.20
    æĿ¾
    -0.20
    igidBody
    -0.19
    leaning
    -0.19
     pu
    -0.19
    éĵ®
    -0.18
    ainties
    -0.18
    VED
    -0.18
    POSITIVE LOGITS
    úsqueda
    0.22
    大家åĪĨ享
    0.22
     dikke
    0.21
     '",
    0.19
    ç©¿æIJŃ
    0.19
    GameManager
    0.19
    .FlatAppearance
    0.19
    ë²¼
    0.18
     scaleX
    0.18
    æİ¥åIJ¬
    0.18
    Activations Density 0.001%

    No Known Activations