© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23059
    Prev
    Next
    INDEX
    Explanations

    announcements about plans

    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
    åģļçļĦäºĭ
    -0.10
    æŶéĹ´åĴĮ
    -0.10
     {}.
    -0.09
    çĶŁäº§åĴĮ
    -0.09
    çŁŃæŶéĹ´åĨħ
    -0.09
     Zucker
    -0.09
    åģļå¾Ĺ
    -0.09
    ä»ĸ认为
    -0.09
    åıįæĺłåĩº
    -0.08
    çıŀ
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.10
    çļĦæŶåĢĻ
    0.10
    ä¸Ģ缴åĪ°
    0.09
    ä¹ĭæĹ¥èµ·
    0.08
     tre
    0.08
     “
    0.08
    tems
    0.08
    çļĦæĻĤåĢĻ
    0.08
    arer
    0.08
     ô
    0.08
    Activations Density 0.545%

    No Known Activations