© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9186
    Prev
    Next
    INDEX
    Explanations

    oxy or xy followed by words

    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
    åıªè¦ģä½ł
    -0.10
    ÑĮ
    -0.10
    èĩ¼
    -0.09
    éĺħ
    -0.09
    ward
    -0.09
    wise
    -0.08
    è´¸
    -0.08
    lessness
    -0.08
    æ²Ļåıij
    -0.08
    éĤ¸
    -0.08
    POSITIVE LOGITS
     Oliv
    0.10
    太åIJİ
    0.09
    æģª
    0.09
    íŀĪ
    0.08
    çĶ¥
    0.08
    éģ¹
    0.08
    娼
    0.08
    ãģĭãģĦ
    0.08
    媾
    0.08
    èģĴ
    0.08
    Activations Density 0.035%

    No Known Activations