© 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. 10096
    Prev
    Next
    INDEX
    Explanations

    train wreck, track, waves, swings

    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
    好çľĭçļĦ
    -0.09
    æŶæŶ
    -0.09
    èµĮ
    -0.09
    æĹĹ
    -0.09
    è¾ľ
    -0.08
    åĺ´å·´
    -0.08
    åŀĤ
    -0.08
    èĩªä¸»åĪĽæĸ°
    -0.08
    好å¤ļ
    -0.08
    ä»ħ代表
    -0.08
    POSITIVE LOGITS
    çļĦç¡®
    0.09
    éļ¾æĢª
    0.09
    é£İæīĩ
    0.09
    -themed
    0.08
     же
    0.08
    æĸĹ
    0.08
    oli
    0.08
    åģı离
    0.08
    onga
    0.08
    irection
    0.08
    Activations Density 0.181%

    No Known Activations