© 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. 52565
    Prev
    Next
    INDEX
    Explanations

    food items: duck, meat, mushrooms, tendon

    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
    æµ·æ´ĭ
    -0.09
     nast
    -0.08
    è¦ģåģļ好
    -0.08
    èĹIJ
    -0.08
     полÑı
    -0.08
    å¸Ĩ
    -0.08
    èĻŀ
    -0.08
    åįĹå±±
    -0.08
    帽
    -0.08
    Fcn
    -0.07
    POSITIVE LOGITS
    alytics
    0.10
    åħŃåIJĪ
    0.10
    æĸĭ
    0.10
    æ¶Īéĺ²å®īåħ¨
    0.09
     kab
    0.09
    çĸ²åĬ³
    0.09
    å½¹
    0.09
    大å¹ħæıIJåįĩ
    0.09
    年产åĢ¼
    0.09
    çĿ¢
    0.09
    Activations Density 0.092%

    No Known Activations