© 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. 37221
    Prev
    Next
    INDEX
    Explanations

    side chains

    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
    æģ¯
    -0.09
    è·³
    -0.08
     Greene
    -0.08
    åħķ
    -0.08
    GRE
    -0.08
    .Singleton
    -0.08
    èĬĴ
    -0.08
    ifest
    -0.08
    çĶµåĬ¨
    -0.08
    _EXTERN
    -0.08
    POSITIVE LOGITS
    éķ¿éķ¿çļĦ
    0.10
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    ä»·ä½į
    0.09
    اسÙĬ
    0.09
    åºŀ大çļĦ
    0.08
    -terminal
    0.08
    åľ¨ä»ĸçļĦ
    0.08
    ardy
    0.08
    主åŁİåĮº
    0.08
     chains
    0.08
    Activations Density 0.517%

    No Known Activations