© 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. 55016
    Prev
    Next
    INDEX
    Explanations

    material, contents, php, anth, ude

    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
    奥
    -0.08
    éĥ½
    -0.08
    ogh
    -0.08
    端
    -0.08
    缸继
    -0.08
    extras
    -0.08
    ãĥ¼ãĤ·
    -0.08
    æİ¥è¿ĩ
    -0.08
     extras
    -0.08
    身影
    -0.08
    POSITIVE LOGITS
    æİĴåĪĹ
    0.10
    åı¯ä»¥èİ·å¾Ĺ
    0.10
    rosso
    0.09
    коп
    0.09
    åı¯ä»¥ä½¿
    0.09
    ä¼ļè®©ä½ł
    0.09
    çªĴ
    0.08
     каÑĤал
    0.08
    è°Ĩ
    0.08
     challeng
    0.08
    Activations Density 0.012%

    No Known Activations