© 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. 27486
    Prev
    Next
    INDEX
    Explanations

    care for self or others

    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
    éŀŃ
    -0.10
    山路
    -0.09
    æįIJ
    -0.09
    åıªæĥ³
    -0.09
     Dana
    -0.08
    详
    -0.08
    ä¸Ńæĸ°ç½ij
    -0.08
     welcome
    -0.08
    å¢ĻéĿ¢
    -0.08
    æĮĩ导æĦıè§ģ
    -0.08
    POSITIVE LOGITS
    身å¿ĥåģ¥åº·
    0.14
    ä¼ĺåħĪ
    0.12
    身ä½ĵåģ¥åº·
    0.11
    èĩªåĬ©
    0.11
    èĩªç§ģ
    0.11
    为èĩªå·±
    0.10
    èĩªèº«çļĦ
    0.10
    ç»Ļèĩªå·±
    0.10
    èĩªæķij
    0.10
    èĩªæĪij
    0.10
    Activations Density 0.047%

    No Known Activations