© 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. 20949
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ä¹ĭæīĢ
    -0.08
    dorf
    -0.08
    ãĥ³ãĤ°
    -0.08
    丹
    -0.08
    ing
    -0.08
    éŀł
    -0.08
    tw
    -0.07
    åīĥ
    -0.07
    unda
    -0.07
    tte
    -0.07
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.10
    åĴĮ个人
    0.10
    å°ıå°ı
    0.09
    é«ĺåĩº
    0.09
    ä¸į认è¯Ĩ
    0.09
    sworth
    0.09
    çĻ«
    0.08
    _widgets
    0.08
    çĶµè§Ĩæľº
    0.08
    ç»ĻäºĨæĪij
    0.08
    Activations Density 0.032%

    No Known Activations