© 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. 37115
    Prev
    Next
    INDEX
    Explanations

    issues and outcomes

    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
    porn
    -0.09
    ä¸įè¦ģåĨį
    -0.09
    åīį身
    -0.09
    æį®æѤ
    -0.08
    åģļçļĦäºĭ
    -0.08
    çļĦåIJĦ项
    -0.08
    оÑĦ
    -0.08
    wright
    -0.08
     horn
    -0.08
    aylight
    -0.08
    POSITIVE LOGITS
    åıĮåıĮ
    0.09
    è¾Ļ
    0.09
    ä¸Ģ缴åĪ°
    0.08
    å½ĵçĦ¶
    0.08
    è¸ı
    0.08
    src
    0.08
    nost
    0.08
    使å¾Ĺ
    0.08
    ce
    0.08
    tex
    0.08
    Activations Density 0.219%

    No Known Activations