© 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. 23241
    Prev
    Next
    INDEX
    Explanations

    aware 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
    ä¸įéĢļ
    -0.08
     Pan
    -0.08
    éĴī
    -0.08
     pan
    -0.08
     mystery
    -0.08
    ç¥ŀç§ĺ
    -0.08
    CBC
    -0.08
    å¿«æĬ¥
    -0.08
    Exclusive
    -0.08
    æľĭåıĭ
    -0.08
    POSITIVE LOGITS
    æĦıè¯ĨåĪ°
    0.21
     aware
    0.21
    aware
    0.21
     awareness
    0.20
    æĦıè¯Ĩ
    0.19
     Aware
    0.18
     Awareness
    0.18
    Aware
    0.16
    -aware
    0.15
    æĦıèŃĺ
    0.15
    Activations Density 0.045%

    No Known Activations