© 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. 37345
    Prev
    Next
    INDEX
    Explanations

    stress, forces, loads, pressure

    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
    欣
    -0.10
    FOX
    -0.09
    ä¼łè¯´
    -0.08
    èĶļ
    -0.08
     trick
    -0.08
    åĹ
    -0.08
     screenHeight
    -0.08
    .definition
    -0.08
     spontaneous
    -0.08
    å¤ĸåľ°
    -0.08
    POSITIVE LOGITS
    åİĭåĬĽ
    0.14
    ä½ľçĶ¨
    0.13
     forces
    0.11
     нагÑĢÑĥз
    0.10
    çļĦåİĭåĬĽ
    0.10
     pressure
    0.10
     stresses
    0.10
     stress
    0.10
    å£ĵåĬĽ
    0.10
    åĬĽè¿ĺæĺ¯
    0.09
    Activations Density 0.207%

    No Known Activations