© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    law or

    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
    weed
    -0.09
    OTS
    -0.09
    antis
    -0.09
    æĶ¶åĪ°äºĨ
    -0.09
    çĤŃ
    -0.09
    å®ĥåı¯ä»¥
    -0.08
    è£ģåijĺ
    -0.08
    èĶĵ
    -0.08
    iest
    -0.08
    åIJĪçIJĨçļĦ
    -0.08
    POSITIVE LOGITS
    itia
    0.10
    æ³°
    0.09
    åıįæĦŁ
    0.09
     TY
    0.09
    èģĮä¸ļ
    0.08
     Jain
    0.08
    è¿Ļä¹Ī大
    0.08
    gow
    0.08
    -submit
    0.08
    uela
    0.08
    Activations Density 0.001%

    No Known Activations