© 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. 8342
    Prev
    Next
    INDEX
    Explanations

    estate of

    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
    åĵº
    -0.12
    æį¢äºĨ
    -0.09
    两级
    -0.09
    ican
    -0.09
    æĴ©
    -0.09
    级以ä¸Ĭ
    -0.08
    é¾Ļ头
    -0.08
    åı±
    -0.08
    æĤĦæĤĦ
    -0.08
    åł°
    -0.08
    POSITIVE LOGITS
    家å±ŀ
    0.16
    家人
    0.13
    亲å±ŀ
    0.11
     families
    0.11
    家éķ¿
    0.11
    åŃIJ女
    0.10
    åŃIJåŃĻ
    0.10
     estates
    0.10
    à¸Ħรà¸Ńà¸ļ
    0.10
     family
    0.10
    Activations Density 0.136%

    No Known Activations