© 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. 37730
    Prev
    Next
    INDEX
    Explanations

    prevention and its aspects

    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
    éĴľ
    -0.10
    ç²ķ
    -0.10
    åįİ举
    -0.10
    ified
    -0.09
    ä¸įéĶĻçļĦ
    -0.09
    åĪ½
    -0.09
    èįı
    -0.09
    âģ¾
    -0.09
    PropertyDescriptor
    -0.08
    åºŁæ°Ķ
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.10
    ä¸ĩä¸Ģ
    0.10
    ramid
    0.09
    ersonic
    0.09
    æŃ
    0.09
    æĢ§
    0.09
    ance
    0.08
    æĦģ
    0.08
    icular
    0.08
    ä¸ĩåįļ
    0.08
    Activations Density 0.038%

    No Known Activations