© 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. 51020
    Prev
    Next
    INDEX
    Explanations

    autonomic nervous system

    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
    åĨĴ
    -0.10
    ä½ľä¸ºä¸ĢåIJį
    -0.10
     Wings
    -0.10
    è¾Ļ
    -0.10
    æĶ¶åıĸ
    -0.10
    åı°éĺ¶
    -0.10
    éĴ©
    -0.09
    RTC
    -0.09
    ä¹Ĵä¹ĵ
    -0.09
    åī
    -0.09
    POSITIVE LOGITS
    Spl
    0.08
    0
    0.08
     gang
    0.08
     oppos
    0.08
    æģ¯
    0.08
    clipboard
    0.08
     deg
    0.08
     reflex
    0.08
    åĥĸ
    0.08
     Net
    0.08
    Activations Density 0.299%

    No Known Activations