© 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. 7612
    Prev
    Next
    INDEX
    Explanations

    consequences of

    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
    ÑĮÑİ
    -0.10
    æºĸ
    -0.09
    æ·¡åĮĸ
    -0.09
    çĻ½èī²çļĦ
    -0.09
    ä¸įå°ij人
    -0.09
    åħ¨ä¸ĸçķĮ
    -0.09
    åı¦ä¸Ģä½į
    -0.09
    ä¸Ńæĸ¹
    -0.09
    æĦıä¹īä¸Ĭ
    -0.09
    å¿Ĵ
    -0.09
    POSITIVE LOGITS
    举åĬ¨
    0.11
    èĮĥ
    0.10
     having
    0.10
    æŃ¤ä¸¾
    0.09
    æľīäºĨ
    0.09
    è¿Ļä¹Īåģļ
    0.09
     actions
    0.09
    having
    0.08
     ÑģлиÑĪ
    0.08
    è¿Ł
    0.08
    Activations Density 0.171%

    No Known Activations