© 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. 20931
    Prev
    Next
    INDEX
    Explanations

    'm the

    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
    éĩįéĩı
    -0.08
    åĭī强
    -0.08
    èī°å·¨
    -0.08
    abor
    -0.08
    Known
    -0.08
    åĨįå¤ļ
    -0.08
    æĪij们å¿ħé¡»
    -0.08
    æĸ°åĬł
    -0.08
    å¥ł
    -0.07
    åĽº
    -0.07
    POSITIVE LOGITS
    èµŀ
    0.10
    亲èĩª
    0.10
     полÑĮз
    0.10
    å¾Īæĸ¹ä¾¿
    0.09
    è¸Ĭè·ĥ
    0.09
    åıĹçĽĬ
    0.09
    åħįè´¹
    0.09
    -upper
    0.09
    èµŀåı¹
    0.09
    çĶľèľľ
    0.09
    Activations Density 0.089%

    No Known Activations