© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4061
    Prev
    Next
    INDEX
    Explanations

    rainforest and Amazon ecosystems

    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
    代表
    -0.08
    亲è¿ij
    -0.08
    ä¹ĭæīĢ
    -0.08
    ArrayOf
    -0.08
    åĨĴ
    -0.08
    æĬ±
    -0.08
     Orn
    -0.08
    æĽĿ
    -0.08
     grease
    -0.08
    éī´
    -0.08
    POSITIVE LOGITS
    æŶåĪ»
    0.10
    åij¼åĶ¤
    0.09
    é¦ĸå¯Į
    0.09
    epam
    0.09
    ç²¾å¯Ĩ
    0.09
    循çݯ
    0.09
    åħ³éĶ®æŶåĪ»
    0.09
    اÙĦÙģ
    0.09
    溥
    0.09
     Stateless
    0.09
    Activations Density 0.064%

    No Known Activations