© 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. 39018
    Prev
    Next
    INDEX
    Explanations

    apparent or perception

    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
    åľ°äº§
    -0.11
    é¢Ħè¨Ģ
    -0.09
    ä¸ĢåĪĨ
    -0.09
     mel
    -0.08
    hem
    -0.08
     bas
    -0.08
    ç¬ijç¬ij
    -0.08
    ither
    -0.08
    继
    -0.08
    har
    -0.08
    POSITIVE LOGITS
    çľĭèµ·ä¾Ĩ
    0.13
    åģĩ
    0.12
    çľĭèµ·æĿ¥
    0.12
     perception
    0.12
     apparent
    0.12
    ä¼ļè§īå¾Ĺ
    0.11
    å°±è§īå¾Ĺ
    0.11
    çľĭä¼¼
    0.11
     perceived
    0.11
    寿
    0.11
    Activations Density 0.121%

    No Known Activations