© 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. 35721
    Prev
    Next
    INDEX
    Explanations

    general anesthesia

    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
     precip
    -0.10
    é¤Ĭ
    -0.09
    æ±¾
    -0.09
    ocl
    -0.09
    icter
    -0.09
    eus
    -0.09
    çĦ¦
    -0.08
    irut
    -0.08
    axy
    -0.08
    å®ŀå®ŀåľ¨åľ¨
    -0.08
    POSITIVE LOGITS
    麻éĨī
    0.17
     anesthesia
    0.10
    çģŃ
    0.10
    ä¼°
    0.09
     LGPL
    0.09
    Invoker
    0.09
    esthesia
    0.09
     дÑĥÑħ
    0.09
    лоÑģÑĮ
    0.08
    Emer
    0.08
    Activations Density 0.231%

    No Known Activations