© 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. 37976
    Prev
    Next
    INDEX
    Explanations

    . followed by sentence start

    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
    å¯ħ
    -0.08
    è´Łè´£
    -0.08
    pper
    -0.08
    çŃīå½¢å¼ı
    -0.08
    çļĦ好å¤Ħ
    -0.08
    ä¸Ģéĺµ
    -0.07
    å¾Īå¿«
    -0.07
    åıĬåħ¶ä»ĸ
    -0.07
    çİĩåħĪ
    -0.07
    åIJIJ
    -0.07
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.12
    贯彻
    0.10
    ä¸ºçĽ®æłĩ
    0.10
    ä¹ĭéģĵ
    0.09
    为æѤ
    0.09
    æIJĶ
    0.09
    inkle
    0.09
    ä½ĵçİ°åľ¨
    0.09
    íķĺìĦ¸ìļĶ
    0.09
    ä¸įæĥľ
    0.09
    Activations Density 0.219%

    No Known Activations