© 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. 52971
    Prev
    Next
    INDEX
    Explanations

    crash and injury

    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
    æĶ¾æĿ¾
    -0.09
    度è¿ĩ
    -0.09
    æĬķåħ¥
    -0.09
    ä¸ĬéĻIJ
    -0.08
    éĢĢå½¹
    -0.08
    æĹłå¿§
    -0.08
    åķĨåĬ¡éĥ¨
    -0.08
    æĿ¾å¼Ľ
    -0.08
     Replies
    -0.08
     deport
    -0.08
    POSITIVE LOGITS
     POD
    0.09
    ëĭ´
    0.09
    æķĻè®Ń
    0.09
    æķ¦
    0.09
    åĪ³
    0.09
    unic
    0.09
    Pod
    0.08
    æĴŀ
    0.08
    æ¯Ĥ
    0.08
    uther
    0.08
    Activations Density 0.063%

    No Known Activations