© 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. 8607
    Prev
    Next
    INDEX
    Explanations

    white corner

    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
    çĭ¸
    -0.09
    é³ĸ
    -0.09
    åĩłåĪĨ
    -0.09
    åħ¬å¸ĥäºĨ
    -0.09
     Darwin
    -0.09
    åĥ»
    -0.09
    åı£åij³
    -0.09
    åIJĪä½ľä¼Ļä¼´
    -0.09
     Press
    -0.08
    Renderer
    -0.08
    POSITIVE LOGITS
    天ä¸Ĭ
    0.11
    æķ´é½IJ
    0.10
     basal
    0.10
    é¢ľèī²
    0.10
    缼å¼Ģ
    0.10
    åĵĹ
    0.09
    ored
    0.09
    æ´ģçĻ½
    0.09
    æĹĴ
    0.09
    æĻĶ
    0.09
    Activations Density 0.089%

    No Known Activations