© 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. 38964
    Prev
    Next
    INDEX
    Explanations

    significant association, amount, or impact

    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
    ack
    -0.09
    ÑĪка
    -0.09
    anked
    -0.09
    ormal
    -0.09
     знаÑĩ
    -0.09
    è¯Ģ
    -0.08
    enate
    -0.08
    stick
    -0.08
    º
    -0.08
     Pics
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.11
     amounts
    0.10
     amount
    0.10
    -sized
    0.10
    iting
    0.09
    æĹłæ¯Ķ
    0.09
    ä¸įäºĨ
    0.09
    leton
    0.09
    itarian
    0.09
    äºİæѤ
    0.09
    Activations Density 0.029%

    No Known Activations