© 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. 36895
    Prev
    Next
    INDEX
    Explanations

    with phrases

    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
    å·²ç»ıæľīäºĨ
    -0.10
    å¤ļåľ°
    -0.10
    为ä¸Ģä½ĵ
    -0.09
     повеÑĢ
    -0.09
    å¹²èĦĨ
    -0.09
    è¿Ļæĺ¯åĽłä¸º
    -0.09
    isci
    -0.09
    çĸ²
    -0.09
    quier
    -0.08
    cus
    -0.08
    POSITIVE LOGITS
     emphasis
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    éĢĤå½ĵçļĦ
    0.09
    asant
    0.09
    ugu
    0.08
    éĢĤå½ĵ
    0.08
    æĪijåİ»
    0.08
    éļĶéŁ³
    0.08
    æģ°å½ĵ
    0.08
     attendant
    0.08
    Activations Density 0.183%

    No Known Activations