© 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. 49669
    Prev
    Next
    INDEX
    Explanations

    blocking or part of words

    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
    ä¸į失
    -0.10
    ÑĪа
    -0.10
    ä¸įä¸Ĭ
    -0.09
    stead
    -0.09
     Ler
    -0.09
    åħ¶ä»ĸ人
    -0.08
    å¤ļäºĨ
    -0.08
    è¦ģæ¯Ķ
    -0.08
    ä¸į让
    -0.08
    ÙħÙĨاط
    -0.08
    POSITIVE LOGITS
    illi
    0.09
    éħ¹
    0.09
    è¯Ł
    0.09
    ä¹łæĥ¯
    0.08
    wash
    0.08
    çħ
    0.08
    çļĦæĸ¹åIJij
    0.08
    驾
    0.08
    éĿ¡
    0.08
    ovsky
    0.08
    Activations Density 0.070%

    No Known Activations