© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7728
    Prev
    Next
    INDEX
    Explanations

    TV television

    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
    bies
    -0.09
    icos
    -0.09
    تص
    -0.09
    ement
    -0.09
    æī®
    -0.08
    von
    -0.08
    ening
    -0.08
    Farm
    -0.08
    ked
    -0.08
    ieder
    -0.08
    POSITIVE LOGITS
    ney
    0.10
    жи
    0.10
    NEY
    0.09
    Compatible
    0.09
    rys
    0.09
    ä¸Ģçľĭ
    0.09
    ç½¹
    0.09
    æ¼¾
    0.09
    åŃľ
    0.09
    åħ¼å®¹
    0.08
    Activations Density 0.004%

    No Known Activations