© 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. 9138
    Prev
    Next
    INDEX
    Explanations

    names ending in "den" or "don"

    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
    isans
    -0.10
    lessly
    -0.09
    enal
    -0.09
    omatic
    -0.09
    usal
    -0.08
    ley
    -0.08
    leys
    -0.08
    æijĬ
    -0.08
    acie
    -0.08
    ttp
    -0.08
    POSITIVE LOGITS
    æģ¤
    0.12
    ä¸Ģ段
    0.11
    aurus
    0.10
    éĿ¢çĽ®
    0.10
    ä¸Ģ份
    0.10
    åķ¡
    0.10
    ä¸Ģè·¯
    0.10
    ä¸Ģéĥ¨
    0.09
    glob
    0.09
    ä¸Ģæŀļ
    0.09
    Activations Density 0.006%

    No Known Activations