© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    Bart names and related surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    teenth
    -0.11
    æѤåĪ»
    -0.09
    ãģ¾ãģĹãģŁ
    -0.09
    гон
    -0.09
    mittel
    -0.09
    /from
    -0.08
    å¤ł
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    ãģİ
    -0.08
    nable
    -0.08
    POSITIVE LOGITS
    .AlertDialog
    0.09
    о
    0.09
    bers
    0.09
    ford
    0.08
    arians
    0.08
    son
    0.08
    oes
    0.08
    itious
    0.08
    inal
    0.08
    ening
    0.08
    Activations Density 0.023%

    No Known Activations