© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53059
    Prev
    Next
    INDEX
    Explanations

    District of Columbia, bisexual, dental, bonuses

    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
    ä¹ĭæĺŁ
    -0.10
    åĺī
    -0.10
    è´¨éĩıåĴĮ
    -0.10
    astr
    -0.09
    cope
    -0.09
    èĿ¶
    -0.09
    ä½Ļ家
    -0.08
    áºŃ
    -0.08
    æľ¬ç§ijçĶŁ
    -0.08
    å¾Īæ¼Ĥ亮
    -0.08
    POSITIVE LOGITS
    循
    0.09
    ç³Ł
    0.08
    anas
    0.08
    ¡
    0.08
    å¾ģæ±ĤæĦıè§ģ
    0.08
    èĤĨ
    0.08
    uhan
    0.08
    EAR
    0.08
    åłĨ
    0.08
     ÐĿи
    0.07
    Activations Density 0.673%

    No Known Activations