© 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. 6781
    Prev
    Next
    INDEX
    Explanations

    raise / create awareness

    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¸Ń举
    -0.09
    еÑĤ
    -0.08
    è¾ĥ大çļĦ
    -0.08
    亵
    -0.08
    伸ãģ³
    -0.08
    ipel
    -0.08
    ç¼Ģ
    -0.08
    rs
    -0.08
    åĨ°åĨ·
    -0.08
    æĺŁçº§éħĴåºĹ
    -0.08
    POSITIVE LOGITS
     awareness
    0.24
    æĦıè¯Ĩ
    0.23
    aware
    0.21
     Awareness
    0.21
    Aware
    0.21
     aware
    0.18
    æĦıè¯ĨåĪ°
    0.17
    -aware
    0.17
    æĦıèŃĺ
    0.16
     consciousness
    0.15
    Activations Density 0.061%

    No Known Activations