© 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. 32082
    Prev
    Next
    INDEX
    Explanations

    put to rest/death/bed/use/sleep

    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
    è¿Īè¿Ľ
    -0.09
    éĻ·åħ¥
    -0.09
    ä¸Ģç»ı
    -0.09
    çĪĨåĩº
    -0.09
    第äºĮå±Ĭ
    -0.09
    å¾Īæľī
    -0.09
    æĹłæ¯Ķ
    -0.09
    ä¾Ľæ±Ĥ
    -0.08
    åıĻ
    -0.08
    и
    -0.08
    POSITIVE LOGITS
    rief
    0.09
    å¤ļä½Ļ
    0.09
    biz
    0.09
    inv
    0.08
    ä¼ĺåĬ¿
    0.08
    yc
    0.08
    诫
    0.08
    æĪĸ许æĺ¯
    0.08
     advantage
    0.08
    åģļçļĦ
    0.08
    Activations Density 0.018%

    No Known Activations