© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    for followed by articles

    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
    æĪij认为
    -0.09
    åħ³äºİæĪij们
    -0.09
    å®ģéĿĻ
    -0.09
    éĢļçŁ¥ä¹¦
    -0.09
    heel
    -0.09
    oru
    -0.09
    Drag
    -0.09
    ody
    -0.09
     pau
    -0.09
    念
    -0.09
    POSITIVE LOGITS
    ipple
    0.11
    ä¹ł
    0.11
    ç¿Ĵ
    0.09
    æĪIJè´¥
    0.09
    æĥħåĨµè¿Ľè¡Į
    0.09
    chw
    0.09
    æ·³
    0.09
    ivery
    0.09
    icorn
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    Activations Density 0.077%

    No Known Activations