© 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. 37366
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    æİ¥åĪ°
    -0.08
    åŃº
    -0.08
    欢è¿İæĤ¨
    -0.08
     Epstein
    -0.08
    ernen
    -0.08
    ÙĤدÙħ
    -0.08
    _mini
    -0.08
    otti
    -0.08
    èĢĨ
    -0.08
    ÑħоÑĤ
    -0.08
    POSITIVE LOGITS
    åĭ¿
    0.12
    è¦ģ好好
    0.11
    çľĭ好
    0.10
    赶快
    0.10
    ä¸įè¦ģ
    0.09
     иÑģполÑĮзоваÑĤÑĮ
    0.09
    åĬ¡å¿ħ
    0.09
    赶紧
    0.09
    ä¸įè¦ģåĨį
    0.09
    çĦ±
    0.09
    Activations Density 0.249%

    No Known Activations