© 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. 22356
    Prev
    Next
    INDEX
    Explanations

    Sudden Infant Death Syndrome

    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
    aniu
    -0.09
    éĴĿ
    -0.09
    ŀæĢ§
    -0.09
    çĿĥ
    -0.09
    ore
    -0.09
     Targets
    -0.08
    çİĩåħĪ
    -0.08
    å¼ĢæĿ¥
    -0.08
    é«ĵ
    -0.08
    å¼ĢéĢļ
    -0.08
    POSITIVE LOGITS
    å©´åĦ¿
    0.12
    å©´
    0.11
    è¥ģ
    0.11
    åºĬä½į
    0.10
    èij¬
    0.09
    嬰
    0.09
    åģľæĶ¾
    0.09
     Ñģог
    0.09
    è´¨éĩıå®īåħ¨
    0.09
     Ride
    0.09
    Activations Density 0.071%

    No Known Activations