© 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. 8953
    Prev
    Next
    INDEX
    Explanations

    clothing for warmth

    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
     trụ
    -0.09
     Dough
    -0.09
    ngr
    -0.09
    å±IJ
    -0.09
    æľ¨è´¨
    -0.09
    çĪª
    -0.09
    äºİæѤ
    -0.09
    пло
    -0.09
    éħ±æ²¹
    -0.08
     Poz
    -0.08
    POSITIVE LOGITS
    è¦ĨçĽĸ
    0.11
    çĦIJ
    0.10
    åŀĤ
    0.10
    çĽĸ
    0.09
    è¦ĨçĽĸçİĩ
    0.09
    Spoiler
    0.09
    èĭ«
    0.09
    covering
    0.08
     flap
    0.08
     spas
    0.08
    Activations Density 0.049%

    No Known Activations