© 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. 17267
    Prev
    Next
    INDEX
    Explanations

    Manabendra, Manito, Manigati, Manocha, Abraham

    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
    è¡·
    -0.09
    odash
    -0.09
    èĨĽ
    -0.09
    stein
    -0.09
    asio
    -0.08
    доб
    -0.08
    _NODES
    -0.08
    æį»
    -0.08
    ä¸Ģ个好çļĦ
    -0.08
    ноп
    -0.08
    POSITIVE LOGITS
    樵
    0.09
    loom
    0.09
     Fridays
    0.08
    è¯ł
    0.08
     Elite
    0.08
    éĺĹ
    0.08
    éĩı
    0.08
    leep
    0.08
    èı¡
    0.08
    pack
    0.08
    Activations Density 0.054%

    No Known Activations