© 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. 36477
    Prev
    Next
    INDEX
    Explanations

    Usain Bolt, Back to the Future

    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
    èģĶéĢļ
    -0.09
    解æĶ¾åĨĽ
    -0.08
    æŀľ
    -0.08
    è§ĤéŁ³
    -0.08
    PRESS
    -0.08
    جار
    -0.08
    åħ°èĬ±
    -0.08
    å·¥å§Ķ
    -0.08
    lda
    -0.08
    etch
    -0.08
    POSITIVE LOGITS
     è¾ĵ
    0.11
    è¾ĵ
    0.10
    åĴĮå®ĮåĸĦ
    0.09
    æŁ°
    0.09
    è¾ĵéĢģ
    0.09
    輸
    0.09
    åıįä¹ĭ
    0.09
    åĢĴ
    0.09
    èIJ¥åķĨ
    0.09
    æºIJæºIJä¸įæĸŃ
    0.09
    Activations Density 0.005%

    No Known Activations