© 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. 37143
    Prev
    Next
    INDEX
    Explanations

    wrongful death lawsuits

    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
    åĪĽä¸ļèĢħ
    -0.09
    æį»
    -0.09
    æĸ°åŁİ
    -0.09
    _perms
    -0.09
    æĭŁ
    -0.09
    踵
    -0.08
    éĹ´éļĻ
    -0.08
    æķijæµİ
    -0.08
    èĥ¥
    -0.08
    å¼ĺ
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľä¸Ń
    0.09
    æĦ§
    0.09
    sez
    0.08
    pii
    0.08
    pard
    0.08
    TRL
    0.08
    pisa
    0.08
    äºĨä¸Ģä¸ĭ
    0.08
    åĽĽçº§
    0.08
    ancell
    0.08
    Activations Density 0.022%

    No Known Activations