© 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. 3891
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    alloca
    -0.21
    PushButton
    -0.20
    },č↵č↵
    -0.20
    被èªī
    -0.20
     sper
    -0.20
    orget
    -0.19
    FXML
    -0.19
    TexParameter
    -0.19
    LastError
    -0.19
    peare
    -0.18
    POSITIVE LOGITS
    .AddSingleton
    0.22
    .='
    0.20
    acerb
    0.19
    ʽ
    0.19
    roupon
    0.19
    ltre
    0.19
    åį¯
    0.19
     RequestMethod
    0.18
    [to
    0.17
     gratuites
    0.17
    Activations Density 0.001%

    No Known Activations