© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38528
    Prev
    Next
    INDEX
    Explanations

    awards

    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
    为åħ¶
    -0.09
    è¾ĥ强
    -0.09
    sonian
    -0.09
    è¾ĥ强çļĦ
    -0.09
    wash
    -0.08
    åģ¥åħ¨
    -0.08
    ivet
    -0.08
    edom
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    å¼·ãģı
    -0.08
    POSITIVE LOGITS
    æĽ³
    0.10
    ä»Ģä¹ĪæŶåĢĻ
    0.09
    åīįå¤ķ
    0.09
    水管
    0.09
    èĬľ
    0.09
    åīª
    0.09
    åıĪè¦ģ
    0.09
    åıĤ
    0.08
    移
    0.08
    кÑĢаÑĤ
    0.08
    Activations Density 0.024%

    No Known Activations