© 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. 1757
    Prev
    Next
    INDEX
    Explanations

    describing or defining terms

    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
    çĽĬ
    -0.10
    æ¥Ķ
    -0.09
    RCT
    -0.08
    ä¸ī家
    -0.08
    æŁĶåĴĮ
    -0.08
    ç»ĩ
    -0.08
    obel
    -0.08
     lab
    -0.08
    亿ä¸ĩ
    -0.08
    builtin
    -0.07
    POSITIVE LOGITS
    ä¿ļ
    0.12
    æ®Ħ
    0.11
    æ¸ħåĩī
    0.11
    æĿ¥å½¢å®¹
    0.11
    æĸ¹è¨Ģ
    0.11
    è°ĥä¾ĥ
    0.11
    形容
    0.10
    çĦ±
    0.10
    åIJĥäºı
    0.10
    æ·ĸ
    0.10
    Activations Density 0.118%

    No Known Activations