© 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. 27331
    Prev
    Next
    INDEX
    Explanations

    sudden onset or disappearance

    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
    尽快
    -0.10
    æŃ¥æŃ¥
    -0.09
     tod
    -0.09
     Larson
    -0.09
    é¢ĵ
    -0.09
    ä¸įèī¯
    -0.08
     autopsy
    -0.08
    积æŀģä½ľçĶ¨
    -0.08
     LCS
    -0.08
    éªĮ
    -0.08
    POSITIVE LOGITS
    å°±è¿Ļä¹Ī
    0.10
    æĹłå£°
    0.10
    ivil
    0.09
    转弯
    0.09
    çªģçĦ¶
    0.09
    çªģå¦Ĥåħ¶
    0.09
    æ¶Ī失
    0.08
    Disappear
    0.08
    æĪIJçĨŁçļĦ
    0.08
     suddenly
    0.08
    Activations Density 0.049%

    No Known Activations