© 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. 11110
    Prev
    Next
    INDEX
    Explanations

    labor and childbirth

    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
    ä¾Ľå¤§å®¶
    -0.09
    çķĮçļĦ
    -0.09
    å°ıæŶåĢĻ
    -0.08
    çĶŁæŃ»
    -0.08
     Mus
    -0.08
    æŃĩ
    -0.08
    åºĹéĩĮ
    -0.08
    ulis
    -0.08
     MMM
    -0.08
    åĬĽæ°Ķ
    -0.08
    POSITIVE LOGITS
    hill
    0.11
    æĿ¥ä¸´
    0.09
    æİĤ
    0.09
    éĻįèĩ³
    0.09
    aghan
    0.08
    æľīåºıæİ¨è¿Ľ
    0.08
    è¿Ń
    0.08
    åĤ¬åĮĸåīĤ
    0.08
    å³Ĵ
    0.08
     cis
    0.08
    Activations Density 0.027%

    No Known Activations