© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    technical or factual

    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
     ModelRenderer
    -0.22
    ä¸Ģ个èģĮä¸ļ
    -0.21
     componentWill
    -0.20
    :animated
    -0.20
    é«Ń
    -0.20
    æľīçļĦçݩ家
    -0.20
    Seleccione
    -0.20
    éļ³
    -0.19
    åŃ£åIJİ
    -0.19
     Dresses
    -0.19
    POSITIVE LOGITS
    é¹³
    0.23
    à¸ķรา
    0.21
    .onView
    0.21
    .hasMore
    0.20
    esub
    0.20
    ogenous
    0.19
    éĹŃ
    0.19
    ÊĮ
    0.18
    夹
    0.18
    ока
    0.18
    Activations Density 0.001%

    No Known Activations