© 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. 36397
    Prev
    Next
    INDEX
    Explanations

    the following word

    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
    人çĶŁçļĦ
    -0.08
    è¿«ä¸įåıĬå¾ħ
    -0.08
    æīĵçĿĢ
    -0.08
    å®ŀçİ°äºĨ
    -0.08
    ayas
    -0.08
    大æī¹
    -0.08
    身å¤Ħ
    -0.08
    ä¸ĸçķĮçļĦ
    -0.08
    éĻĨç»Ń
    -0.08
    crest
    -0.08
    POSITIVE LOGITS
    缮çļĦæĺ¯
    0.10
    è¶Ĭå¤ļ
    0.09
    æĥŁ
    0.09
    åıĸåĨ³äºİ
    0.09
     reason
    0.09
     aim
    0.09
    éĴ¿
    0.09
    ä¸įèĩ³äºİ
    0.09
    çıŃ主任
    0.09
     оÑģобенно
    0.09
    Activations Density 0.319%

    No Known Activations