© 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. 52098
    Prev
    Next
    INDEX
    Explanations

    playing musical instruments

    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¦Ļ
    -0.09
    afs
    -0.08
    PID
    -0.08
    inel
    -0.08
    drag
    -0.08
    ä»»ä½ķ人éĥ½
    -0.08
    ä¸ĢåıĮ
    -0.08
    åıĮæīĭ
    -0.08
     jumper
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
    POSITIVE LOGITS
    æĹ¶æľº
    0.11
    桧
    0.09
    åıĪ好
    0.09
     tạm
    0.09
    åħ¨æĹ¥
    0.09
    icket
    0.09
    çĪ±ä½ł
    0.09
    æĸ°å¼Ģ
    0.09
    éĽªå±±
    0.09
    ãģŁãģı
    0.09
    Activations Density 0.016%

    No Known Activations