© 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. 32659
    Prev
    Next
    INDEX
    Explanations

    indicates advice or capabilities

    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
    åĪĨæĺİ
    -0.09
    伶
    -0.09
    满满
    -0.08
    é¦Ħ
    -0.08
    请大家
    -0.08
    åºĶ该å¦Ĥä½ķ
    -0.08
    ãģĬãģĭãģĴ
    -0.08
    æľ¬æľŁ
    -0.08
    åIJĮä»ģ
    -0.08
    æľĭåıĭ们
    -0.07
    POSITIVE LOGITS
    é¢ĺ主
    0.15
    楼主
    0.12
    å¸®ä½ł
    0.10
     ÐĴам
    0.09
     ÑĦоÑĢÑĥм
    0.09
    âĨ³
    0.09
    ç§ģãĤĤ
    0.09
    ãģ§ãģĹãĤĩãģĨãģŃ
    0.09
    elenium
    0.09
    ä½łåı¯ä»¥
    0.09
    Activations Density 1.106%

    No Known Activations