© 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. 19602
    Prev
    Next
    INDEX
    Explanations

    negative outcomes ending in death or failure

    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
    ä¸į妨
    -0.10
    æļĤ
    -0.09
    èĮµ
    -0.09
    ä¸įç®¡ä½ł
    -0.08
    æľį饰
    -0.08
    éªģ
    -0.08
    æĥķ
    -0.08
    æŀģå°ij
    -0.08
    ä¸į论æĺ¯
    -0.08
    æĹ¥æ¸IJ
    -0.08
    POSITIVE LOGITS
    OTS
    0.10
    ãģ°ãģĭãĤĬ
    0.09
    æĮ¨
    0.09
    å°±æѤ
    0.09
    åŀĴ
    0.09
    칫
    0.08
    EXTERN
    0.08
     march
    0.08
    ä½ĨçĶ±äºİ
    0.08
    åīįè¿Ľ
    0.08
    Activations Density 0.196%

    No Known Activations