© 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. 36944
    Prev
    Next
    INDEX
    Explanations

    overseeing operations or programs

    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
    tering
    -0.11
    主ä¹īæĢĿæĥ³
    -0.10
    -found
    -0.09
    ç´į
    -0.09
    Assignable
    -0.09
    ä¹ĭ声
    -0.08
    ilda
    -0.08
    ãĥ¼ãĤ¸
    -0.08
    ä¼ĺåħĪ
    -0.08
    å¸ģ
    -0.08
    POSITIVE LOGITS
    大å±Ģ
    0.12
    大èĩ´
    0.10
    åħ·ä½ĵæĥħåĨµ
    0.09
    pper
    0.09
    onest
    0.09
    彤
    0.09
    alling
    0.09
    箩
    0.09
    ingly
    0.08
    BIND
    0.08
    Activations Density 0.007%

    No Known Activations