© 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. 51962
    Prev
    Next
    INDEX
    Explanations

    age of, age-old

    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
    çݰ代社ä¼ļ
    -0.09
    å½ĵæŶ
    -0.09
    å½ĵæŶçļĦ
    -0.09
    è½¼
    -0.08
    å¤ĸè§Ĥ
    -0.08
    çİĭåĽ½
    -0.08
    sov
    -0.08
    sink
    -0.08
    elly
    -0.08
    çķ¶æĻĤ
    -0.08
    POSITIVE LOGITS
    ç»Ħå§Ķä¼ļ
    0.11
    liness
    0.10
    ãģ¶ãĤĬ
    0.10
    ä¹ĭ称
    0.09
    æĿ¥ä¸´
    0.09
    icated
    0.09
     Bender
    0.09
    éļĪ
    0.09
    ë³Ħ
    0.09
    бÑĥ
    0.09
    Activations Density 0.018%

    No Known Activations