© 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. 7445
    Prev
    Next
    INDEX
    Explanations

    government or official titles

    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
    -times
    -0.09
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    æľ¬äºº
    -0.08
    iki
    -0.08
    享åıĹ
    -0.08
    åıĹçĽĬ
    -0.08
    æĺĬ
    -0.08
    æĮ¥æīĭ
    -0.08
    ä¹į
    -0.08
     Mol
    -0.08
    POSITIVE LOGITS
    å®ĺåijĺ
    0.14
    çŃīéĥ¨éŨ
    0.13
     commissioner
    0.10
    æĶ¹éĿ©
    0.10
    è´Łè´£äºº
    0.10
    èģĮèĥ½
    0.10
     officials
    0.10
    å·¥ä½ľäººåijĺ
    0.09
    ç½²
    0.09
    è¡Ļ
    0.09
    Activations Density 0.178%

    No Known Activations