© 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. 52080
    Prev
    Next
    INDEX
    Explanations

    controller hub chip

    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
    å¼ĢåıijèĢħ
    -0.09
     phosphate
    -0.08
    飶
    -0.08
    躺çĿĢ
    -0.08
    raz
    -0.08
    éĽ¯
    -0.08
    çı¥
    -0.08
    常æĢģ
    -0.08
    rary
    -0.08
    èĩªä¹ł
    -0.08
    POSITIVE LOGITS
    ÑģоÑģ
    0.09
    illard
    0.09
    常è§ģçļĦ
    0.09
     Scratch
    0.09
    ç«ĭæ¡Ī
    0.09
    çĩĥæĸĻ
    0.09
    å°ıå§ijå¨ĺ
    0.09
    ä¸ĩäºĭ
    0.08
     Barker
    0.08
    èĤļ
    0.08
    Activations Density 0.023%

    No Known Activations