© 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. 26833
    Prev
    Next
    INDEX
    Explanations

    loss of function on thawing

    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¶³å¤Ł
    -0.09
    ç«ŁçĦ¶
    -0.09
    æĪij们åºĶ该
    -0.09
    梨
    -0.09
    ç¾Ĭ
    -0.08
    zac
    -0.08
    æĺ¨å¤©
    -0.08
    å®ģæĦ¿
    -0.08
    æĺİæĺİ
    -0.08
    åıĪ被
    -0.08
    POSITIVE LOGITS
     limited
    0.11
     пÑĢидеÑĤÑģÑı
    0.11
    å±ĢéĻIJ
    0.10
    失åİ»
    0.10
     ÙĪسÙĬ
    0.09
     Limited
    0.09
     assured
    0.09
    Limited
    0.09
    å±ĢéĻIJäºİ
    0.09
    è¿ĺæĺ¯ä¼ļ
    0.09
    Activations Density 0.116%

    No Known Activations