© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    life on earth

    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
    æĴ
    -0.10
    è´ŁéĿ¢
    -0.09
    ä¸Ģå¤Ħ
    -0.09
     Sabb
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    éĵ¨
    -0.09
    èIJį
    -0.08
    为ä»Ģä¹Īä¸į
    -0.08
    æİ¥å¾ħ
    -0.08
    POSITIVE LOGITS
    çĶŁåij½
    0.12
    çļĦçĶŁåij½
    0.12
    åĪ·
    0.10
     life
    0.10
    liv
    0.10
     leven
    0.09
    zell
    0.09
    稳
    0.09
    eselect
    0.09
     жизни
    0.09
    Activations Density 0.055%

    No Known Activations