© 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. 20653
    Prev
    Next
    INDEX
    Explanations

    royalty-free license

    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
    禺
    -0.09
    ä¸įæŃ»
    -0.09
    èĩĤ
    -0.09
    룡
    -0.09
    ä½ľèĢħæīĢæľī
    -0.09
    icone
    -0.09
    缩水
    -0.08
    ʳ
    -0.08
    æĪijçĪ¸
    -0.08
    Spoiler
    -0.08
    POSITIVE LOGITS
    åīį线
    0.08
    sect
    0.08
    orig
    0.08
    çłĴ
    0.08
     conclusion
    0.08
    uries
    0.08
    åīįçŀ»
    0.08
    åIJ¬è§ģ
    0.08
    ç¨İè´¹
    0.08
     whenever
    0.08
    Activations Density 0.011%

    No Known Activations