© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    one of a kind

    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
    isoft
    -0.09
    æŃ£å½ĵ
    -0.09
    è¡·
    -0.09
    èİł
    -0.09
     Äijây
    -0.09
    bü
    -0.09
    è¤Ĭ
    -0.08
    åIJĦçķĮ
    -0.08
    é²
    -0.08
    éĩįçĤ¹é¢ĨåŁŁ
    -0.08
    POSITIVE LOGITS
    meal
    0.08
    æ¢Ń
    0.08
    liner
    0.08
    off
    0.08
    åĩ¤åĩ°
    0.08
    å¢ĥ
    0.08
    æŃ»åİ»
    0.08
    nels
    0.07
    ç¨į
    0.07
    ẫn
    0.07
    Activations Density 0.006%

    No Known Activations