© 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. 37226
    Prev
    Next
    INDEX
    Explanations

    I see, I found, I want

    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
    æ´İ
    -0.11
    æĸŃ
    -0.10
    ubern
    -0.09
    æĸ·
    -0.09
    çĶĦ
    -0.09
    榴
    -0.09
    (Target
    -0.09
    ãģķãģĪ
    -0.08
     mole
    -0.08
    åIJĪæł¼
    -0.08
    POSITIVE LOGITS
    è¡ĮæĶ¿åĮº
    0.10
    OrNull
    0.09
    红楼
    0.09
    社ä¼ļæķĪçĽĬ
    0.09
    åı«åģļ
    0.08
     Gujar
    0.08
    akest
    0.08
     happening
    0.08
    amil
    0.08
    称ä¹ĭ为
    0.08
    Activations Density 0.103%

    No Known Activations