© 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. 1844
    Prev
    Next
    INDEX
    Explanations

    code and technical files

    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
    __);
    -0.24
    MMdd
    -0.24
    Č
    -0.24
    __;
    -0.23
    ()>↵
    -0.22
    .AWS
    -0.21
    "f
    -0.20
    VICE
    -0.20
    çĺ¸
    -0.20
    ATEGORY
    -0.19
    POSITIVE LOGITS
    yal
    0.21
     "";č↵č↵
    0.20
    æ»ı
    0.20
    ittle
    0.20
    ķĮ
    0.20
    иденÑĤ
    0.20
     Playoff
    0.19
     metic
    0.18
    apixel
    0.18
     intimid
    0.18
    Activations Density 0.001%

    No Known Activations