© 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. 9227
    Prev
    Next
    INDEX
    Explanations

    submit or press to confirm

    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
    夹
    -0.12
    ç»ĵæŀĦè°ĥæķ´
    -0.09
    leri
    -0.09
    æĪ´
    -0.09
    æĿ¥äºĨ
    -0.08
    ãĤ¹ãĤ¿ãĥ³
    -0.08
    èĩªä¸»
    -0.08
     Jeremiah
    -0.08
    ucks
    -0.08
    èIJĮ
    -0.08
    POSITIVE LOGITS
    å°±åı¯ä»¥äºĨ
    0.13
    submit
    0.12
    æıIJ交
    0.11
    -submit
    0.10
    åIJİæŀľ
    0.10
     submit
    0.10
    æİ£
    0.10
    æĪijçľĭ
    0.09
    otton
    0.09
    éĢĴ交
    0.09
    Activations Density 0.122%

    No Known Activations