© 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. 51289
    Prev
    Next
    INDEX
    Explanations

    financial valuation or description

    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
    arius
    -0.10
    秣æĪ¿
    -0.09
    é«ĺé¢ij
    -0.09
    å²ģçļĦ
    -0.09
    èIJ¥ä¸ļé¢Ŀ
    -0.08
    å®°
    -0.08
    ÙħÙĨت
    -0.08
    é¢ijç¹ģ
    -0.08
     StringUtil
    -0.08
    лÑĮн
    -0.08
    POSITIVE LOGITS
    认è´Ń
    0.12
    æ¯ıèĤ¡
    0.10
    æĿĥåĪ©
    0.10
    æĿĥçĽĬ
    0.10
    éĢĢ
    0.09
    å±ĬæŶ
    0.09
    GetData
    0.09
    çĽĪ
    0.09
    对åħ¬åı¸
    0.09
    å¤ĦåĪĨ
    0.08
    Activations Density 0.033%

    No Known Activations