© 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. 8754
    Prev
    Next
    INDEX
    Explanations

    erasing or removing

    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
    uss
    -0.10
    å¼ĵ
    -0.09
    zzo
    -0.09
    룬
    -0.09
     MISS
    -0.09
    ä½İä¸ĭ
    -0.09
    æĸľ
    -0.08
    å¼¥
    -0.08
    ToWorld
    -0.08
    عÙĦÙħ
    -0.08
    POSITIVE LOGITS
    æİīäºĨ
    0.11
    å¹²åĩĢ
    0.10
    æĵ¦
    0.09
    æİī
    0.09
    èĥľè´Ł
    0.09
    çľĭä¸įè§ģ
    0.09
    欢快
    0.09
    äºĨä»ĸçļĦ
    0.09
    äº®çľ¼
    0.09
    enha
    0.08
    Activations Density 0.016%

    No Known Activations