© 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. 36835
    Prev
    Next
    INDEX
    Explanations

    us and you

    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
    åľ¾
    -0.09
    Unchecked
    -0.09
    PO
    -0.09
    3
    -0.09
    2
    -0.08
    æĪij家
    -0.08
    çļĦæĪ¿åŃIJ
    -0.08
    ä¸Ģèīĺ
    -0.08
    åł¡
    -0.08
     Owners
    -0.08
    POSITIVE LOGITS
    们
    0.11
    æŶä¸įæŶ
    0.10
    家ä¼Ļ
    0.10
    ä»ij
    0.09
    phem
    0.09
    çī¹æĿĥ
    0.09
    æ°ijåĬŀ
    0.08
    æľīä¿¡å¿ĥ
    0.08
    erte
    0.08
    åħļåijĺ
    0.08
    Activations Density 0.059%

    No Known Activations