© 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. 20452
    Prev
    Next
    INDEX
    Explanations

    problem, guide, demo, issue, blog, course

    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
    راء
    -0.09
    å§Ĵ
    -0.08
    âĢ¹
    -0.08
    æľīéĴĪ对æĢ§
    -0.08
    段
    -0.08
    ottle
    -0.08
    éĢĨ
    -0.08
    ühl
    -0.07
    semble
    -0.07
    addons
    -0.07
    POSITIVE LOGITS
    éĢŀ
    0.10
    sto
    0.10
    ãģªãĤĵãģ¦
    0.09
    å¯ĵ
    0.09
    nelle
    0.09
    åIJĥæĥĬ
    0.09
     kern
    0.09
    èĩªæĿ¥
    0.09
     maté
    0.09
    æĶĺ
    0.09
    Activations Density 0.461%

    No Known Activations