© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9004
    Prev
    Next
    INDEX
    Explanations

    promote business

    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
    ERN
    -0.10
    åĩĨ
    -0.09
    æĮĩæĮ¥
    -0.09
    溢
    -0.09
    outh
    -0.09
    å¯ĨåĪĩåħ³æ³¨
    -0.09
    ÑĤан
    -0.08
    èģļçĦ¦
    -0.08
    ä¸Ĭ课
    -0.08
    oll
    -0.08
    POSITIVE LOGITS
    宣æī¬
    0.11
    以éĺ²
    0.09
    æī©æķ£
    0.09
    å®£ä¼łæ´»åĬ¨
    0.09
    åĩºåİ»
    0.08
    å®£ä¼ł
    0.08
    éĥ¨åī¯
    0.08
    è§Ĥ念
    0.08
    æĺ¼å¤ľ
    0.08
    çŁ¥åIJį度
    0.08
    Activations Density 0.052%

    No Known Activations