© 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. 31460
    Prev
    Next
    INDEX
    Explanations

    storage items or devices

    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
    å¾Ĺ天
    -0.10
    æĦŁè§¦
    -0.10
    让çĶ¨æĪ·
    -0.10
    奶
    -0.10
    彬
    -0.09
    çļĦæŃ¥ä¼IJ
    -0.09
    oday
    -0.09
    eed
    -0.09
    æĮĩåIJij
    -0.09
    åįİ缼
    -0.09
    POSITIVE LOGITS
    à¹Ħว
    0.09
    éĺ´éĺ³
    0.09
    æĶ¾åľ¨
    0.09
    éĻĪåĪĹ
    0.09
    è¿ľæĸ¹
    0.08
    æIJģ
    0.08
    olin
    0.08
     trophies
    0.08
    åĿIJ
    0.08
     shelf
    0.08
    Activations Density 0.080%

    No Known Activations