© 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. 37109
    Prev
    Next
    INDEX
    Explanations

    summer activities and events

    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
    UME
    -0.10
    HING
    -0.10
    sync
    -0.10
    sel
    -0.09
    sat
    -0.09
    su
    -0.09
    sr
    -0.09
    raries
    -0.09
    edly
    -0.09
    å°¼æĸ¯
    -0.09
    POSITIVE LOGITS
    oral
    0.11
    hall
    0.11
    ized
    0.10
    atoria
    0.10
    lane
    0.09
    land
    0.09
    ous
    0.09
    lich
    0.09
    æľīä¸Ģ天
    0.09
    aneously
    0.09
    Activations Density 0.029%

    No Known Activations