© 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. 37151
    Prev
    Next
    INDEX
    Explanations

    be used / described

    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
    管çIJĨåĴĮ
    -0.11
    并å°Ĩ
    -0.11
    建设åĴĮ
    -0.11
    èĥ½åĬĽåĴĮ
    -0.10
    并ä¸Ķ
    -0.10
    çIJĨ解åĴĮ
    -0.10
    並ä¸Ķ
    -0.10
    æĬĢæľ¯åĴĮ
    -0.09
    æŶéĹ´åĴĮ
    -0.09
    å¹¶åľ¨
    -0.09
    POSITIVE LOGITS
    大家ä¸Ģèµ·
    0.12
    åĬłä»¥
    0.12
    为ä¹ĭ
    0.11
    /OR
    0.10
    åĽłæѤ
    0.10
    缸åºĶçļĦ
    0.10
    çĮ´
    0.09
    å¹´ä¹ĭä¹ħ
    0.09
    éľ²åĩº
    0.09
     PREFIX
    0.09
    Activations Density 0.395%

    No Known Activations