© 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. 27694
    Prev
    Next
    INDEX
    Explanations

    optimization, research, ranking, PPC

    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
    笫
    -0.09
    åıįçľģ
    -0.09
    åĶ¯
    -0.09
    çıŀ
    -0.09
    è´´
    -0.09
     Johns
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    паÑģ
    -0.08
    èĢĨ
    -0.08
    鹧
    -0.08
    POSITIVE LOGITS
    楼
    0.09
    ittel
    0.09
    ioni
    0.08
    è¿ĻæĶ¯
    0.08
    çİ°åĩº
    0.08
    åĪ»
    0.08
    èįĨ
    0.08
    anton
    0.08
    ÑĢож
    0.08
    æݬ
    0.08
    Activations Density 0.025%

    No Known Activations