© 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. 53149
    Prev
    Next
    INDEX
    Explanations

    aloe vera juice or leaves

    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
    Ð¡ÐŁ
    -0.10
    rad
    -0.09
    éĻĦ
    -0.09
    ä¸įä¸ĭ
    -0.09
    åIJİå¤ĩ
    -0.09
    å¤įåIJĪ
    -0.08
     ÐŀÑĩ
    -0.08
    èIJ½ä¸ĭ
    -0.08
    rost
    -0.08
    åħ¨èº«
    -0.08
    POSITIVE LOGITS
    榨
    0.09
    æĦī
    0.09
    æ¿ł
    0.09
    aska
    0.09
    çīĪæĿĥ声æĺİ
    0.09
    åĮĹ京æŶéĹ´
    0.09
    æ±ģ
    0.09
    zo
    0.09
    åĴĮå¹³
    0.09
    èĩªå¾ĭ
    0.09
    Activations Density 0.065%

    No Known Activations