© 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. 8119
    Prev
    Next
    INDEX
    Explanations

    calendar year or event

    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
    lessly
    -0.10
    ä¸Ģåı£
    -0.09
    äºĨä¸Ģåı£
    -0.09
    alent
    -0.09
    elage
    -0.09
    rist
    -0.09
    å®ļæľŁ
    -0.09
    人æ°Ķ
    -0.09
    eve
    -0.08
    éģı
    -0.08
    POSITIVE LOGITS
    ize
    0.10
    ised
    0.09
    ä¸ĬçļĦ
    0.09
    CriticalSection
    0.08
    å¹´åIJİ
    0.08
    åıªä¸º
    0.08
    æŃ¤äºº
    0.08
    ized
    0.08
     sclerosis
    0.08
    åħ±åĴĮåĽ½
    0.08
    Activations Density 0.011%

    No Known Activations