© 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. 55505
    Prev
    Next
    INDEX
    Explanations

    bacteria and soil science

    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
    主ä½ĵ
    -0.10
     mall
    -0.10
    æľį
    -0.09
    èķ¨
    -0.09
    mal
    -0.09
    å¸ĺ
    -0.08
    éĢ¼
    -0.08
    lemn
    -0.08
    便æį·
    -0.08
    imas
    -0.08
    POSITIVE LOGITS
    ç§ijæĬĢèĤ¡ä»½
    0.09
    æ¯ı个人çļĦ
    0.09
    訴
    0.09
    è¿Ļæł·ä¸Ģ
    0.09
     globe
    0.08
    èĮ¹
    0.08
    åľĥ
    0.08
    çIJĥåľº
    0.08
    vo
    0.08
    åĿĽ
    0.08
    Activations Density 0.183%

    No Known Activations