© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20420
    Prev
    Next
    INDEX
    Explanations

    impose

    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
    olog
    -0.09
    emen
    -0.09
     Wich
    -0.09
    leen
    -0.09
    æľī人
    -0.09
    æīĭä¸Ĭ
    -0.08
    goog
    -0.08
    zo
    -0.08
    fields
    -0.07
    æ³Ķ
    -0.07
    POSITIVE LOGITS
    è¿Ļ个ä¸ĸçķĮ
    0.12
    æķ´ä¸ª
    0.12
    åIJİæİĴ
    0.11
    åħ¨ä½ĵ
    0.10
    çĶ¨æĪ·æıIJä¾Ľ
    0.10
    è¿ĻæĶ¯
    0.10
    æķ´åĢĭ
    0.10
    è¿Ļ座åŁİå¸Ĥ
    0.10
    æķ´ä¸ªäºº
    0.10
    æ²»çIJĨä½ĵç³»
    0.10
    Activations Density 0.097%

    No Known Activations