© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10144
    Prev
    Next
    INDEX
    Explanations

    adversity, hardship, or ending

    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
    æ´¥
    -0.11
    ä»ĸ们æĺ¯
    -0.09
    æĥĬåĸľ
    -0.09
    å°ıå·§
    -0.09
     Tel
    -0.09
    åįģåħ«å±Ĭ
    -0.09
    她们
    -0.09
    çĹĴ
    -0.08
    ä¸ĸ代
    -0.08
    ä»ĸ们
    -0.08
    POSITIVE LOGITS
    éħĹ
    0.16
    åIJ¸æ¯Ĵ
    0.14
    çļĦ人çĶŁ
    0.12
    éħĴç²¾
    0.11
     алкогол
    0.10
     alcohol
    0.10
    人çĶŁ
    0.10
    coc
    0.10
    æ¯Ĵåĵģ
    0.09
    æĬ½çĥŁ
    0.09
    Activations Density 0.085%

    No Known Activations