© 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. 37584
    Prev
    Next
    INDEX
    Explanations

    stress

    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
    æ£ł
    -0.11
    linger
    -0.11
     GroupLayout
    -0.10
    è¹Ī
    -0.10
    æľĽåİ»
    -0.09
    å°ļ
    -0.09
    moth
    -0.09
    ModelAttribute
    -0.09
    клÑİÑĩен
    -0.09
    chemy
    -0.09
    POSITIVE LOGITS
     stress
    0.24
     Stress
    0.21
    stress
    0.21
    ãĤ¹ãĥĪãĥ¬ãĤ¹
    0.20
    åºĶåĬĽ
    0.19
    åİĭåĬĽ
    0.18
     stressful
    0.18
    ç´§å¼ł
    0.18
    çĦ¦èĻij
    0.16
     stressed
    0.14
    Activations Density 0.174%

    No Known Activations