© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30152
    Prev
    Next
    INDEX
    Explanations

    caregivers or carers

    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
    çĪ±ç¾İ
    -0.09
    itet
    -0.09
    æķŀ
    -0.08
    å¦ŀ
    -0.08
    缴èIJ¥
    -0.08
    زاÙĦ
    -0.08
    å«ĸ
    -0.08
    äºijéĽĨ
    -0.08
    åºĨåħ¸
    -0.08
    çįł
    -0.08
    POSITIVE LOGITS
    ä¹īåĬ¡
    0.15
    è´Łæĭħ
    0.14
    家åĬ¡
    0.14
    æĭħ
    0.14
    è§Ĵèī²
    0.12
    æī¿æĭħ
    0.12
    æĹłåģ¿
    0.12
    義åĭĻ
    0.12
     unpaid
    0.12
    æīĵæī«
    0.12
    Activations Density 0.127%

    No Known Activations