© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    parts or portions 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
    æĽ´å¥½åľ°
    -0.11
    Ñĭва
    -0.09
    proper
    -0.09
    æľīçļĦ
    -0.09
    大巴
    -0.09
    æĽ´å¥½
    -0.09
    çķ¥å¾®
    -0.09
    æĽ´å¤ļ
    -0.09
     Proper
    -0.08
     proper
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.12
    ä¹ĥèĩ³
    0.12
    å°¤åħ¶æĺ¯
    0.09
    åı¯è§Ĥ
    0.09
    lay
    0.09
    åľ¨åħ¶
    0.08
    以èĩ³äºİ
    0.08
    课åłĤæķĻåѦ
    0.08
     alm
    0.08
    ç½ijåıĭè¯Ħ论
    0.08
    Activations Density 0.040%

    No Known Activations