© 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. 35433
    Prev
    Next
    INDEX
    Explanations

    copyright notices and ownership

    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
    åĨµ
    -0.09
     اÙĦشر
    -0.09
    éĩįç£ħ
    -0.09
    éĩįè¦ģåĽłç´ł
    -0.09
     Creed
    -0.09
    产åĩº
    -0.09
    cape
    -0.09
    oret
    -0.08
    æĹ·
    -0.08
    обÑĢаз
    -0.08
    POSITIVE LOGITS
    äº
    0.08
    ÑĤÑĢ
    0.08
    æ¢ĵ
    0.08
    第ä¸īæĸ¹
    0.08
    reuse
    0.08
    å¨Ł
    0.08
    åŁ´
    0.08
    ÑĤеÑĢ
    0.08
    elu
    0.08
    agar
    0.08
    Activations Density 0.042%

    No Known Activations