© 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. 36379
    Prev
    Next
    INDEX
    Explanations

    don't let

    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¯
    -0.11
    æģª
    -0.10
    å°´å°¬
    -0.10
    æ¯ĭ
    -0.10
    ä¸įä½Ĩ
    -0.10
    æIJĶ
    -0.09
    ä¸ĩç¾İåħĥ
    -0.09
    ä¸Ńéĵģ
    -0.09
    éĩįè¦ģåİŁåĽł
    -0.09
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    POSITIVE LOGITS
    enders
    0.10
     pans
    0.10
    ä½İä»·
    0.09
    ä¸Ļ
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    éĤ£äºĽ
    0.08
    ức
    0.08
     necessarily
    0.08
    åĩ½
    0.08
    umar
    0.08
    Activations Density 0.014%

    No Known Activations