© 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. 58945
    Prev
    Next
    INDEX
    Explanations

    can do

    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
    æĬĬä½ł
    -0.17
    ä½łéľĢè¦ģ
    -0.14
     yourself
    -0.14
    å½ĵä½ł
    -0.13
    è®©ä½ł
    -0.13
    å¯¹ä½ł
    -0.13
    ä½łçļĦ
    -0.13
    ä½łå°±
    -0.13
    åĽłä¸ºä½ł
    -0.13
    ä¸ºä½ł
    -0.13
    POSITIVE LOGITS
     themselves
    0.17
    åºĶ注æĦı
    0.11
    楮
    0.10
    ä½Ĩä»ĸ们
    0.10
    ä»ĸèĩªå·±
    0.09
    à¸Ńม
    0.09
    =cut
    0.09
     ìŀIJìĭł
    0.09
    庶
    0.09
    åºĶ该å¦Ĥä½ķ
    0.09
    Activations Density 0.102%

    No Known Activations