© 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. 21274
    Prev
    Next
    INDEX
    Explanations

    class or variable name identifiers

    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
    çĦ¶æĺ¯
    -0.10
    liner
    -0.10
    gers
    -0.09
    ness
    -0.09
    quet
    -0.08
    panse
    -0.08
    ä½Ĩä»į
    -0.08
    uai
    -0.08
    ency
    -0.08
    åıijæĶ¹
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.09
    çļĦåIJįåŃĹ
    0.09
    Ùı
    0.08
    asy
    0.08
    èķĥ
    0.08
    éĹ´çļĦ
    0.08
    Stan
    0.08
    åºĬåŀ«
    0.08
    ä¹ĭä½Ļ
    0.08
    çļĦèģĮä¸ļ
    0.08
    Activations Density 0.058%

    No Known Activations