© 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. 51403
    Prev
    Next
    INDEX
    Explanations

    actors and awards

    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
    ä»Ģ
    -0.09
    åı¼
    -0.09
    æİĴæ¯Ĵ
    -0.09
     пеÑĢвÑĥÑİ
    -0.08
    åħ³éĶ®æĺ¯
    -0.08
     пÑĢин
    -0.08
     Strom
    -0.08
    深深
    -0.08
    æ¥Ŀ
    -0.08
    \Context
    -0.08
    POSITIVE LOGITS
    astr
    0.10
    aug
    0.09
    审
    0.09
    dog
    0.09
    æ°´ä¸Ĭ
    0.08
    å§IJ
    0.08
    åŁŁ
    0.08
    åĢŁ
    0.08
    模仿
    0.08
    å¡«
    0.08
    Activations Density 0.004%

    No Known Activations