© 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. 20430
    Prev
    Next
    INDEX
    Explanations

    emphasizing or emphasis

    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
    liness
    -0.10
    pedia
    -0.10
    ying
    -0.10
    ural
    -0.09
    house
    -0.09
    inary
    -0.09
    ish
    -0.09
    ton
    -0.09
    utc
    -0.09
    ç´§å¼ł
    -0.09
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.10
    ç¯ĵ
    0.09
    elves
    0.09
    глав
    0.09
    azen
    0.09
    ãĥ³ãĤ°
    0.09
    个人è§ĤçĤ¹
    0.09
    ãģ£ãģįãĤĬ
    0.09
    ockets
    0.09
    ãģĩ
    0.08
    Activations Density 0.007%

    No Known Activations