© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    specific numbers and quantities

    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
    é¾Ł
    -0.10
    è¿Ļ个è¡Įä¸ļ
    -0.10
    èĩªçIJĨ
    -0.09
    åĴ½
    -0.09
    çĶµæ¢¯
    -0.09
    CLU
    -0.09
    家ä¼Ļ
    -0.09
    åĴĮåľ°åĮº
    -0.09
    üzü
    -0.09
    akers
    -0.09
    POSITIVE LOGITS
    ç½ij绾å®īåħ¨
    0.08
     courtesy
    0.08
    姹
    0.08
    å¢Ł
    0.08
    ardy
    0.08
    salt
    0.08
    å¢ŀ
    0.07
    åij½åIJį为
    0.07
     dream
    0.07
     ubiqu
    0.07
    Activations Density 0.219%

    No Known Activations