© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7885
    Prev
    Next
    INDEX
    Explanations

    how much something is worth

    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
    å¯Įæ°ij
    -0.08
     extents
    -0.08
    isters
    -0.08
    书åºĹ
    -0.08
    çĶ¨èį¯
    -0.08
    çĮľæĥ³
    -0.08
    çĶŁæ´»ä¹łæĥ¯
    -0.08
    å¸ĥç½®
    -0.08
    è¥Ł
    -0.08
    _ENV
    -0.08
    POSITIVE LOGITS
    ä»·åĢ¼
    0.21
    åĥ¹åĢ¼
    0.18
    çļĦä»·åĢ¼
    0.16
    å¢ŀåĢ¼
    0.16
     ê°Ģì¹ĺ
    0.15
    æľīä»·åĢ¼
    0.15
     value
    0.13
    çıįè´µ
    0.13
    åįĩåĢ¼
    0.12
     worth
    0.12
    Activations Density 0.060%

    No Known Activations