© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35718
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    erness
    -0.11
    ç³Ļ
    -0.09
    mate
    -0.09
    æķ¦
    -0.09
    kins
    -0.09
    uten
    -0.08
    ãĥ¼ãĥ³
    -0.08
     اÙĦجÙĪ
    -0.08
    chants
    -0.08
    æłĵ
    -0.08
    POSITIVE LOGITS
    itis
    0.11
    åħīçݯ
    0.10
    acia
    0.10
    è®®äºĭ
    0.10
    大åħ¨
    0.10
    اÙĥ
    0.10
    éĨĴæĿ¥
    0.09
    ä¸įäºĨ解
    0.09
    å¡Ķ
    0.09
    éĽī
    0.09
    Activations Density 0.024%

    No Known Activations